Common Weakness Enumeration

CWE-1427

Allowed

Improper Neutralization of Input Used for LLM Prompting

Abstraction: Base · Status: Incomplete

API response cwe.mitre.org

The product uses externally-provided data to build prompts provided to large language models (LLMs), but the way these prompts are constructed causes the LLM to fail to distinguish between user-supplied inputs and developer provided system directives.

28 vulnerabilities reference this CWE, most recent first.

CVE-2026-75130 (GCVE-0-2026-75130)

Vulnerability from cvelistv5 – Published: 2026-08-18 18:02 – Updated: 2026-08-19 15:14
VLAI
Title
Context7 2.1.2 Prompt Injection via Custom AI Instructions
Summary
Context7 through 2.1.2 contains a prompt injection vulnerability that allows attackers to execute malicious instructions in connected AI coding agents by injecting unsanitized content through the Custom AI Instructions feature served via the MCP server. Attackers can poison the custom instructions to exfiltrate credentials from environment files to an attacker-controlled service and perform destructive file deletion on the victim's machine when the agent makes a routine library documentation request.
Severity
6.4 (Medium)
CVSS:4.0/AV:N/AC:L/AT:N/PR:L/UI:P/VC:N/VI:N/VA:N/SC:H/SI:H/SA:H
9 (Critical)
CVSS:3.1/AV:N/AC:L/PR:L/UI:R/S:C/C:H/I:H/A:H
SSVC
Exploitation: none Automatable: no Technical Impact: total
CISA Coordinator · CISA-ADP (v2.0.3)
Decision recorded 2026-08-19 15:14 UTC
CWE
  • CWE-1427 - Improper Neutralization of Input Used for LLM Prompting
Assigner
VulnCheck CNA
References
Impacted products
Vendor Product Version
Uptash Context7 Affected: 0 , ≤ 2.1.2 (semver)
Create a notification for this product.
Date Public
2026-03-05 00:00
Credits
Eli Ainhorn - Senior AI Vulnerability Researcher @ Noma Security
Show details on NVD website
To clipboard 

{
  "containers": {
    "adp": [
      {
        "metrics": [
          {
            "other": {
              "content": {
                "id": "CVE-2026-75130",
                "options": [
                  {
                    "Exploitation": "none"
                  },
                  {
                    "Automatable": "no"
                  },
                  {
                    "Technical Impact": "total"
                  }
                ],
                "role": "CISA Coordinator",
                "timestamp": "2026-08-19T15:14:18.244695Z",
                "version": "2.0.3"
              },
              "type": "ssvc"
            }
          }
        ],
        "providerMetadata": {
          "dateUpdated": "2026-08-19T15:14:32.042Z",
          "orgId": "134c704f-9b21-4f2e-91b3-4a467353bcc0",
          "shortName": "CISA-ADP"
        },
        "title": "CISA ADP Vulnrichment"
      }
    ],
    "cna": {
      "affected": [
        {
          "defaultStatus": "affected",
          "product": "Context7",
          "vendor": "Uptash",
          "versions": [
            {
              "lessThanOrEqual": "2.1.2",
              "status": "affected",
              "version": "0",
              "versionType": "semver"
            }
          ]
        }
      ],
      "credits": [
        {
          "lang": "en",
          "type": "finder",
          "value": "Eli Ainhorn - Senior AI Vulnerability Researcher @ Noma Security"
        }
      ],
      "datePublic": "2026-03-05T00:00:00.000Z",
      "descriptions": [
        {
          "lang": "en",
          "value": "Context7 through 2.1.2 contains a prompt injection vulnerability that allows attackers to execute malicious instructions in connected AI coding agents by injecting unsanitized content through the Custom AI Instructions feature served via the MCP server. Attackers can poison the custom instructions to exfiltrate credentials from environment files to an attacker-controlled service and perform destructive file deletion on the victim\u0027s machine when the agent makes a routine library documentation request."
        }
      ],
      "metrics": [
        {
          "cvssV4_0": {
            "Automatable": "NOT_DEFINED",
            "Recovery": "NOT_DEFINED",
            "Safety": "NOT_DEFINED",
            "attackComplexity": "LOW",
            "attackRequirements": "NONE",
            "attackVector": "NETWORK",
            "baseScore": 6.4,
            "baseSeverity": "MEDIUM",
            "exploitMaturity": "NOT_DEFINED",
            "privilegesRequired": "LOW",
            "providerUrgency": "NOT_DEFINED",
            "subAvailabilityImpact": "HIGH",
            "subConfidentialityImpact": "HIGH",
            "subIntegrityImpact": "HIGH",
            "userInteraction": "PASSIVE",
            "valueDensity": "NOT_DEFINED",
            "vectorString": "CVSS:4.0/AV:N/AC:L/AT:N/PR:L/UI:P/VC:N/VI:N/VA:N/SC:H/SI:H/SA:H",
            "version": "4.0",
            "vulnAvailabilityImpact": "NONE",
            "vulnConfidentialityImpact": "NONE",
            "vulnIntegrityImpact": "NONE",
            "vulnerabilityResponseEffort": "NOT_DEFINED"
          },
          "format": "CVSS",
          "scenarios": [
            {
              "lang": "en",
              "value": "GENERAL"
            }
          ]
        },
        {
          "cvssV3_1": {
            "attackComplexity": "LOW",
            "attackVector": "NETWORK",
            "availabilityImpact": "HIGH",
            "baseScore": 9,
            "baseSeverity": "CRITICAL",
            "confidentialityImpact": "HIGH",
            "integrityImpact": "HIGH",
            "privilegesRequired": "LOW",
            "scope": "CHANGED",
            "userInteraction": "REQUIRED",
            "vectorString": "CVSS:3.1/AV:N/AC:L/PR:L/UI:R/S:C/C:H/I:H/A:H",
            "version": "3.1"
          },
          "format": "CVSS",
          "scenarios": [
            {
              "lang": "en",
              "value": "GENERAL"
            }
          ]
        }
      ],
      "problemTypes": [
        {
          "descriptions": [
            {
              "cweId": "CWE-1427",
              "description": "Improper Neutralization of Input Used for LLM Prompting",
              "lang": "en",
              "type": "CWE"
            }
          ]
        }
      ],
      "providerMetadata": {
        "dateUpdated": "2026-08-18T18:57:30.864Z",
        "orgId": "83251b91-4cc7-4094-a5c7-464a1b83ea10",
        "shortName": "VulnCheck"
      },
      "references": [
        {
          "name": "Noma Security Blog",
          "tags": [
            "technical-description",
            "exploit"
          ],
          "url": "https://noma.security/blog/contextcrush-context7-the-mcp-server-vulnerability/"
        },
        {
          "name": "Supplier LinkedIn Post",
          "tags": [
            "vendor-advisory"
          ],
          "url": "https://www.linkedin.com/posts/upstash_mcp-server-vulnerability-in-context-7-activity-7435686676049387520-PBVo/"
        },
        {
          "tags": [
            "third-party-advisory"
          ],
          "url": "https://www.vulncheck.com/advisories/context7-prompt-injection-via-custom-ai-instructions"
        }
      ],
      "source": {
        "discovery": "UNKNOWN"
      },
      "title": "Context7 2.1.2 Prompt Injection via Custom AI Instructions",
      "x_generator": {
        "engine": "vulncheck"
      }
    }
  },
  "cveMetadata": {
    "assignerOrgId": "83251b91-4cc7-4094-a5c7-464a1b83ea10",
    "assignerShortName": "VulnCheck",
    "cveId": "CVE-2026-75130",
    "datePublished": "2026-08-18T18:02:37.331Z",
    "dateReserved": "2026-08-17T18:39:57.660Z",
    "dateUpdated": "2026-08-19T15:14:32.042Z",
    "state": "PUBLISHED"
  },
  "dataType": "CVE_RECORD",
  "dataVersion": "5.2"
}

CVE-2026-70331 (GCVE-0-2026-70331)

Vulnerability from cvelistv5 – Published: 2026-08-28 17:41 – Updated: 2026-10-30 17:19
VLAI
Title
Microsoft Edge for iOS Spoofing Vulnerability
Summary
Improper neutralization of input used for llm prompting in Microsoft Edge for iOS allows an unauthorized attacker to perform spoofing over a network.
Severity
5.4 (Medium)
CVSS:3.1/AV:N/AC:L/PR:N/UI:R/S:U/C:L/I:L/A:N/E:U/RL:O/RC:C
SSVC
Exploitation: none Automatable: no Technical Impact: partial
CISA Coordinator · CISA-ADP (v2.0.3)
Decision recorded 2026-08-31 15:21 UTC
CWE
  • CWE-1427 - Improper Neutralization of Input Used for LLM Prompting
Assigner
microsoft CNA
References
Impacted products
Vendor Product Version
Microsoft Microsoft Edge (Chromium-based) Affected: 1.0.0.0 , < 150.0.4078.50 (custom)
Create a notification for this product.
Microsoft Microsoft Edge for iOS Affected: 1.0.0.0 , < 150.0.4078.50 (custom)
Create a notification for this product.
Date Public
2026-08-28 14:00
Show details on NVD website
To clipboard 

{
  "containers": {
    "adp": [
      {
        "metrics": [
          {
            "other": {
              "content": {
                "id": "CVE-2026-70331",
                "options": [
                  {
                    "Exploitation": "none"
                  },
                  {
                    "Automatable": "no"
                  },
                  {
                    "Technical Impact": "partial"
                  }
                ],
                "role": "CISA Coordinator",
                "timestamp": "2026-08-31T15:21:22.059696Z",
                "version": "2.0.3"
              },
              "type": "ssvc"
            }
          }
        ],
        "providerMetadata": {
          "dateUpdated": "2026-08-31T18:54:20.048Z",
          "orgId": "134c704f-9b21-4f2e-91b3-4a467353bcc0",
          "shortName": "CISA-ADP"
        },
        "title": "CISA ADP Vulnrichment"
      }
    ],
    "cna": {
      "affected": [
        {
          "product": "Microsoft Edge (Chromium-based)",
          "vendor": "Microsoft",
          "versions": [
            {
              "lessThan": "150.0.4078.50",
              "status": "affected",
              "version": "1.0.0.0",
              "versionType": "custom"
            }
          ]
        },
        {
          "product": "Microsoft Edge for iOS",
          "vendor": "Microsoft",
          "versions": [
            {
              "lessThan": "150.0.4078.50",
              "status": "affected",
              "version": "1.0.0.0",
              "versionType": "custom"
            }
          ]
        }
      ],
      "cpeApplicability": [
        {
          "nodes": [
            {
              "cpeMatch": [
                {
                  "criteria": "cpe:2.3:a:microsoft:edge_chromium:*:*:*:*:*:*:*:*",
                  "versionEndExcluding": "150.0.4078.50",
                  "versionStartIncluding": "1.0.0.0",
                  "vulnerable": true
                },
                {
                  "criteria": "cpe:2.3:a:microsoft:edge:*:*:*:*:*:iphone_os:*:*",
                  "versionEndExcluding": "150.0.4078.50",
                  "versionStartIncluding": "1.0.0.0",
                  "vulnerable": true
                }
              ],
              "negate": false,
              "operator": "OR"
            }
          ]
        }
      ],
      "datePublic": "2026-08-28T14:00:00.000Z",
      "descriptions": [
        {
          "lang": "en-US",
          "value": "Improper neutralization of input used for llm prompting in Microsoft Edge for iOS allows an unauthorized attacker to perform spoofing over a network."
        }
      ],
      "metrics": [
        {
          "cvssV3_1": {
            "baseScore": 5.4,
            "baseSeverity": "MEDIUM",
            "vectorString": "CVSS:3.1/AV:N/AC:L/PR:N/UI:R/S:U/C:L/I:L/A:N/E:U/RL:O/RC:C",
            "version": "3.1"
          },
          "format": "CVSS",
          "scenarios": [
            {
              "lang": "en-US",
              "value": "GENERAL"
            }
          ]
        }
      ],
      "problemTypes": [
        {
          "descriptions": [
            {
              "cweId": "CWE-1427",
              "description": "CWE-1427: Improper Neutralization of Input Used for LLM Prompting",
              "lang": "en-US",
              "type": "CWE"
            }
          ]
        }
      ],
      "providerMetadata": {
        "dateUpdated": "2026-10-30T17:19:26.402Z",
        "orgId": "f38d906d-7342-40ea-92c1-6c4a2c6478c8",
        "shortName": "microsoft"
      },
      "references": [
        {
          "name": "Microsoft Edge for iOS Spoofing Vulnerability",
          "tags": [
            "vendor-advisory",
            "patch"
          ],
          "url": "https://msrc.microsoft.com/update-guide/vulnerability/CVE-2026-70331"
        }
      ],
      "title": "Microsoft Edge for iOS Spoofing Vulnerability"
    }
  },
  "cveMetadata": {
    "assignerOrgId": "f38d906d-7342-40ea-92c1-6c4a2c6478c8",
    "assignerShortName": "microsoft",
    "cveId": "CVE-2026-70331",
    "datePublished": "2026-08-28T17:41:29.160Z",
    "dateReserved": "2026-08-04T00:04:56.036Z",
    "dateUpdated": "2026-10-30T17:19:26.402Z",
    "state": "PUBLISHED"
  },
  "dataType": "CVE_RECORD",
  "dataVersion": "5.2"
}

CVE-2026-54142 (GCVE-0-2026-54142)

Vulnerability from cvelistv5 – Published: 2026-11-05 16:42 – Updated: 2026-11-05 18:24
VLAI
Title
OpenHuman: Indirect prompt injection via background email sync executes Composio actions without user approval
Summary
OpenHuman is an open-source agent harness available as a desktop application and Rust library. Before 0.57.13, background synchronization for connected services such as email, Slack, and Notion stores raw external content and later places it in the model context of autonomous background agents without neutralizing embedded instructions. ApprovalGate treats tool calls without an interactive chat context as pre-authorized automation, so attacker-authored content processed during a background tick can influence the model to invoke Composio actions without presenting an approval request. An attacker who can deliver content to a connected account can use this path to send or forward data, post messages, create or modify third-party content, or disclose information from OpenHuman memory and integrations. The issue requires an active integration and successful model interpretation of the injected instructions. This issue is fixed in version 0.57.13.
Severity
8.7 (High)
CVSS:3.1/AV:N/AC:H/PR:N/UI:N/S:C/C:H/I:H/A:N
SSVC
Exploitation: poc Automatable: no Technical Impact: total
CISA Coordinator · CISA-ADP (v2.0.3)
Decision recorded 2026-11-05 18:24 UTC
CWE
Assigner
GitHub_M CNA
References
Impacted products
Vendor Product Version
tinyhumansai openhuman Affected: < 0.57.13
Create a notification for this product.
Show details on NVD website
To clipboard 

{
  "containers": {
    "adp": [
      {
        "metrics": [
          {
            "other": {
              "content": {
                "id": "CVE-2026-54142",
                "options": [
                  {
                    "Exploitation": "poc"
                  },
                  {
                    "Automatable": "no"
                  },
                  {
                    "Technical Impact": "total"
                  }
                ],
                "role": "CISA Coordinator",
                "timestamp": "2026-11-05T18:24:02.444218Z",
                "version": "2.0.3"
              },
              "type": "ssvc"
            }
          }
        ],
        "providerMetadata": {
          "dateUpdated": "2026-11-05T18:24:38.878Z",
          "orgId": "134c704f-9b21-4f2e-91b3-4a467353bcc0",
          "shortName": "CISA-ADP"
        },
        "references": [
          {
            "tags": [
              "exploit"
            ],
            "url": "https://github.com/tinyhumansai/openhuman/security/advisories/GHSA-p9gw-q7cf-57qr"
          }
        ],
        "title": "CISA ADP Vulnrichment"
      }
    ],
    "cna": {
      "affected": [
        {
          "product": "openhuman",
          "vendor": "tinyhumansai",
          "versions": [
            {
              "status": "affected",
              "version": "\u003c 0.57.13"
            }
          ]
        }
      ],
      "descriptions": [
        {
          "lang": "en",
          "value": "OpenHuman is an open-source agent harness available as a desktop application and Rust library. Before 0.57.13, background synchronization for connected services such as email, Slack, and Notion stores raw external content and later places it in the model context of autonomous background agents without neutralizing embedded instructions. ApprovalGate treats tool calls without an interactive chat context as pre-authorized automation, so attacker-authored content processed during a background tick can influence the model to invoke Composio actions without presenting an approval request. An attacker who can deliver content to a connected account can use this path to send or forward data, post messages, create or modify third-party content, or disclose information from OpenHuman memory and integrations. The issue requires an active integration and successful model interpretation of the injected instructions. This issue is fixed in version 0.57.13."
        }
      ],
      "metrics": [
        {
          "cvssV3_1": {
            "attackComplexity": "HIGH",
            "attackVector": "NETWORK",
            "availabilityImpact": "NONE",
            "baseScore": 8.7,
            "baseSeverity": "HIGH",
            "confidentialityImpact": "HIGH",
            "integrityImpact": "HIGH",
            "privilegesRequired": "NONE",
            "scope": "CHANGED",
            "userInteraction": "NONE",
            "vectorString": "CVSS:3.1/AV:N/AC:H/PR:N/UI:N/S:C/C:H/I:H/A:N",
            "version": "3.1"
          }
        }
      ],
      "problemTypes": [
        {
          "descriptions": [
            {
              "cweId": "CWE-1427",
              "description": "CWE-1427:",
              "lang": "en",
              "type": "CWE"
            }
          ]
        }
      ],
      "providerMetadata": {
        "dateUpdated": "2026-11-05T16:42:19.275Z",
        "orgId": "a0819718-46f1-4df5-94e2-005712e83aaa",
        "shortName": "GitHub_M"
      },
      "references": [
        {
          "name": "https://github.com/tinyhumansai/openhuman/security/advisories/GHSA-p9gw-q7cf-57qr",
          "tags": [
            "x_refsource_CONFIRM"
          ],
          "url": "https://github.com/tinyhumansai/openhuman/security/advisories/GHSA-p9gw-q7cf-57qr"
        },
        {
          "name": "https://github.com/tinyhumansai/openhuman/pull/3227",
          "tags": [
            "x_refsource_MISC"
          ],
          "url": "https://github.com/tinyhumansai/openhuman/pull/3227"
        },
        {
          "name": "https://github.com/tinyhumansai/openhuman/commit/3a7180da7765af861bf44d79e025fc67dbeae0ca",
          "tags": [
            "x_refsource_MISC"
          ],
          "url": "https://github.com/tinyhumansai/openhuman/commit/3a7180da7765af861bf44d79e025fc67dbeae0ca"
        },
        {
          "name": "https://github.com/tinyhumansai/openhuman/releases/tag/v0.57.13",
          "tags": [
            "x_refsource_MISC"
          ],
          "url": "https://github.com/tinyhumansai/openhuman/releases/tag/v0.57.13"
        }
      ],
      "source": {
        "advisory": "GHSA-p9gw-q7cf-57qr",
        "discovery": "UNKNOWN"
      },
      "title": "OpenHuman: Indirect prompt injection via background email sync executes Composio actions without user approval"
    }
  },
  "cveMetadata": {
    "assignerOrgId": "a0819718-46f1-4df5-94e2-005712e83aaa",
    "assignerShortName": "GitHub_M",
    "cveId": "CVE-2026-54142",
    "datePublished": "2026-11-05T16:42:19.275Z",
    "dateReserved": "2026-06-11T21:15:33.871Z",
    "dateUpdated": "2026-11-05T18:24:38.878Z",
    "state": "PUBLISHED"
  },
  "dataType": "CVE_RECORD",
  "dataVersion": "5.2"
}

CVE-2026-54140 (GCVE-0-2026-54140)

Vulnerability from cvelistv5 – Published: 2026-11-05 16:13 – Updated: 2026-11-09 17:19
VLAI
Title
OpenHuman: MCP tool description injection: untrusted server descriptions execute in agent LLM context without sanitization
Summary
OpenHuman is an open-source agent harness available as a desktop application and Rust library. Before 0.57.13, OpenHuman places names, descriptions, titles, and parameter definitions returned by configured external MCP servers into the agent model context without neutralizing instructions or bounding the descriptive fields. The McpRemoteTool records produced by list_tools preserve this remote content, while tool filtering considers the tool name and the prompt-injection detector screens user messages rather than MCP definitions. A malicious or compromised MCP server can therefore return a poisoned description that is evaluated on every agent turn and may direct the model to invoke other available tools, disclose accessible data, or perform unauthorized actions without a separate malicious user message. The issue affects users who configure an attacker-controlled or compromised MCP server. This issue is fixed in version 0.57.13.
Severity
8.3 (High)
CVSS:3.1/AV:N/AC:H/PR:N/UI:R/S:C/C:H/I:H/A:H
SSVC
Exploitation: poc Automatable: no Technical Impact: total
CISA Coordinator · CISA-ADP (v2.0.3)
Decision recorded 2026-11-09 17:18 UTC
CWE
Assigner
GitHub_M CNA
References
Impacted products
Vendor Product Version
tinyhumansai openhuman Affected: < 0.57.13
Create a notification for this product.
Show details on NVD website
To clipboard 

{
  "containers": {
    "adp": [
      {
        "metrics": [
          {
            "other": {
              "content": {
                "id": "CVE-2026-54140",
                "options": [
                  {
                    "Exploitation": "poc"
                  },
                  {
                    "Automatable": "no"
                  },
                  {
                    "Technical Impact": "total"
                  }
                ],
                "role": "CISA Coordinator",
                "timestamp": "2026-11-09T17:18:30.482758Z",
                "version": "2.0.3"
              },
              "type": "ssvc"
            }
          }
        ],
        "providerMetadata": {
          "dateUpdated": "2026-11-09T17:19:01.138Z",
          "orgId": "134c704f-9b21-4f2e-91b3-4a467353bcc0",
          "shortName": "CISA-ADP"
        },
        "references": [
          {
            "tags": [
              "exploit"
            ],
            "url": "https://github.com/tinyhumansai/openhuman/security/advisories/GHSA-g6j9-89xv-v752"
          }
        ],
        "title": "CISA ADP Vulnrichment"
      }
    ],
    "cna": {
      "affected": [
        {
          "product": "openhuman",
          "vendor": "tinyhumansai",
          "versions": [
            {
              "status": "affected",
              "version": "\u003c 0.57.13"
            }
          ]
        }
      ],
      "descriptions": [
        {
          "lang": "en",
          "value": "OpenHuman is an open-source agent harness available as a desktop application and Rust library. Before 0.57.13, OpenHuman places names, descriptions, titles, and parameter definitions returned by configured external MCP servers into the agent model context without neutralizing instructions or bounding the descriptive fields. The McpRemoteTool records produced by list_tools preserve this remote content, while tool filtering considers the tool name and the prompt-injection detector screens user messages rather than MCP definitions. A malicious or compromised MCP server can therefore return a poisoned description that is evaluated on every agent turn and may direct the model to invoke other available tools, disclose accessible data, or perform unauthorized actions without a separate malicious user message. The issue affects users who configure an attacker-controlled or compromised MCP server. This issue is fixed in version 0.57.13."
        }
      ],
      "metrics": [
        {
          "cvssV3_1": {
            "attackComplexity": "HIGH",
            "attackVector": "NETWORK",
            "availabilityImpact": "HIGH",
            "baseScore": 8.3,
            "baseSeverity": "HIGH",
            "confidentialityImpact": "HIGH",
            "integrityImpact": "HIGH",
            "privilegesRequired": "NONE",
            "scope": "CHANGED",
            "userInteraction": "REQUIRED",
            "vectorString": "CVSS:3.1/AV:N/AC:H/PR:N/UI:R/S:C/C:H/I:H/A:H",
            "version": "3.1"
          }
        }
      ],
      "problemTypes": [
        {
          "descriptions": [
            {
              "cweId": "CWE-1427",
              "description": "CWE-1427:",
              "lang": "en",
              "type": "CWE"
            }
          ]
        }
      ],
      "providerMetadata": {
        "dateUpdated": "2026-11-05T16:13:31.126Z",
        "orgId": "a0819718-46f1-4df5-94e2-005712e83aaa",
        "shortName": "GitHub_M"
      },
      "references": [
        {
          "name": "https://github.com/tinyhumansai/openhuman/security/advisories/GHSA-g6j9-89xv-v752",
          "tags": [
            "x_refsource_CONFIRM"
          ],
          "url": "https://github.com/tinyhumansai/openhuman/security/advisories/GHSA-g6j9-89xv-v752"
        },
        {
          "name": "https://github.com/tinyhumansai/openhuman/pull/3215",
          "tags": [
            "x_refsource_MISC"
          ],
          "url": "https://github.com/tinyhumansai/openhuman/pull/3215"
        },
        {
          "name": "https://github.com/tinyhumansai/openhuman/commit/00b8a669c6e6391a1be9f724bd9c8f755ee3c43e",
          "tags": [
            "x_refsource_MISC"
          ],
          "url": "https://github.com/tinyhumansai/openhuman/commit/00b8a669c6e6391a1be9f724bd9c8f755ee3c43e"
        },
        {
          "name": "https://github.com/tinyhumansai/openhuman/releases/tag/v0.57.13",
          "tags": [
            "x_refsource_MISC"
          ],
          "url": "https://github.com/tinyhumansai/openhuman/releases/tag/v0.57.13"
        }
      ],
      "source": {
        "advisory": "GHSA-g6j9-89xv-v752",
        "discovery": "UNKNOWN"
      },
      "title": "OpenHuman: MCP tool description injection: untrusted server descriptions execute in agent LLM context without sanitization"
    }
  },
  "cveMetadata": {
    "assignerOrgId": "a0819718-46f1-4df5-94e2-005712e83aaa",
    "assignerShortName": "GitHub_M",
    "cveId": "CVE-2026-54140",
    "datePublished": "2026-11-05T16:13:31.126Z",
    "dateReserved": "2026-06-11T21:15:33.870Z",
    "dateUpdated": "2026-11-09T17:19:01.138Z",
    "state": "PUBLISHED"
  },
  "dataType": "CVE_RECORD",
  "dataVersion": "5.2"
}

CVE-2026-46580 (GCVE-0-2026-46580)

Vulnerability from cvelistv5 – Published: 2026-06-18 14:26 – Updated: 2026-06-19 03:55
VLAI
Summary
In Eclipse Theia versions prior to 1.71.0, files matching the pattern .prompts/*.prompttemplate in a workspace were automatically loaded and could override or extend the AI agent's system prompts. An attacker could craft a malicious repository containing prompt template files that, when the workspace was opened in Theia, replaced the AI's system instructions with attacker-controlled content (indirect prompt injection). Combined with other AI chat features available in untrusted workspaces, this enabled attack chains leading to data exfiltration via Markdown image rendering or arbitrary command execution via task definitions.
Severity
8.4 (High)
CVSS:4.0/AV:L/AC:L/AT:N/PR:N/UI:A/VC:H/VI:H/VA:H/SC:N/SI:N/SA:N
SSVC
Exploitation: none Automatable: no Technical Impact: total
CISA Coordinator · CISA-ADP (v2.0.3)
Decision recorded 2026-06-18 00:00 UTC
CWE
  • CWE-829 - Inclusion of Functionality from Untrusted Control Sphere
  • CWE-1427 - Improper Neutralization of Input Used for LLM Prompting
Assigner
eclipse CNA
References
Impacted products
Vendor Product Version
Eclipse Foundation Eclipse Theia Affected: 0 , < 1.71.0 (semver)
Create a notification for this product.
Credits
Piotr Ryciak (https://gitlab.eclipse.org/void01)
Show details on NVD website
To clipboard 

{
  "containers": {
    "adp": [
      {
        "metrics": [
          {
            "other": {
              "content": {
                "id": "CVE-2026-46580",
                "options": [
                  {
                    "Exploitation": "none"
                  },
                  {
                    "Automatable": "no"
                  },
                  {
                    "Technical Impact": "total"
                  }
                ],
                "role": "CISA Coordinator",
                "timestamp": "2026-06-18T00:00:00+00:00",
                "version": "2.0.3"
              },
              "type": "ssvc"
            }
          }
        ],
        "providerMetadata": {
          "dateUpdated": "2026-06-19T03:55:46.723Z",
          "orgId": "134c704f-9b21-4f2e-91b3-4a467353bcc0",
          "shortName": "CISA-ADP"
        },
        "title": "CISA ADP Vulnrichment"
      }
    ],
    "cna": {
      "affected": [
        {
          "defaultStatus": "unaffected",
          "product": "Eclipse Theia",
          "repo": "https://github.com/eclipse-theia/theia",
          "vendor": "Eclipse Foundation",
          "versions": [
            {
              "lessThan": "1.71.0",
              "status": "affected",
              "version": "0",
              "versionType": "semver"
            }
          ]
        }
      ],
      "credits": [
        {
          "lang": "en",
          "type": "finder",
          "value": "Piotr Ryciak (https://gitlab.eclipse.org/void01)"
        }
      ],
      "descriptions": [
        {
          "lang": "en",
          "supportingMedia": [
            {
              "base64": false,
              "type": "text/html",
              "value": "In Eclipse Theia versions prior to 1.71.0, files matching the pattern \u003ccode\u003e.prompts/*.prompttemplate\u003c/code\u003e in a workspace were automatically loaded and could override or extend the AI agent\u0027s system prompts. An attacker could craft a malicious repository containing prompt template files that, when the workspace was opened in Theia, replaced the AI\u0027s system instructions with attacker-controlled content (indirect prompt injection). Combined with other AI chat features available in untrusted workspaces, this enabled attack chains leading to data exfiltration via Markdown image rendering or arbitrary command execution via task definitions."
            }
          ],
          "value": "In Eclipse Theia versions prior to 1.71.0, files matching the pattern .prompts/*.prompttemplate in a workspace were automatically loaded and could override or extend the AI agent\u0027s system prompts. An attacker could craft a malicious repository containing prompt template files that, when the workspace was opened in Theia, replaced the AI\u0027s system instructions with attacker-controlled content (indirect prompt injection). Combined with other AI chat features available in untrusted workspaces, this enabled attack chains leading to data exfiltration via Markdown image rendering or arbitrary command execution via task definitions."
        }
      ],
      "metrics": [
        {
          "cvssV4_0": {
            "Automatable": "NOT_DEFINED",
            "Recovery": "NOT_DEFINED",
            "Safety": "NOT_DEFINED",
            "attackComplexity": "LOW",
            "attackRequirements": "NONE",
            "attackVector": "LOCAL",
            "baseScore": 8.4,
            "baseSeverity": "HIGH",
            "exploitMaturity": "NOT_DEFINED",
            "privilegesRequired": "NONE",
            "providerUrgency": "NOT_DEFINED",
            "subAvailabilityImpact": "NONE",
            "subConfidentialityImpact": "NONE",
            "subIntegrityImpact": "NONE",
            "userInteraction": "ACTIVE",
            "valueDensity": "NOT_DEFINED",
            "vectorString": "CVSS:4.0/AV:L/AC:L/AT:N/PR:N/UI:A/VC:H/VI:H/VA:H/SC:N/SI:N/SA:N",
            "version": "4.0",
            "vulnAvailabilityImpact": "HIGH",
            "vulnConfidentialityImpact": "HIGH",
            "vulnIntegrityImpact": "HIGH",
            "vulnerabilityResponseEffort": "NOT_DEFINED"
          },
          "format": "CVSS",
          "scenarios": [
            {
              "lang": "en",
              "value": "GENERAL"
            }
          ]
        }
      ],
      "problemTypes": [
        {
          "descriptions": [
            {
              "cweId": "CWE-829",
              "description": "CWE-829: Inclusion of Functionality from Untrusted Control Sphere",
              "lang": "en",
              "type": "CWE"
            }
          ]
        },
        {
          "descriptions": [
            {
              "cweId": "CWE-1427",
              "description": "CWE-1427: Improper Neutralization of Input Used for LLM Prompting",
              "lang": "en",
              "type": "CWE"
            }
          ]
        }
      ],
      "providerMetadata": {
        "dateUpdated": "2026-06-18T14:26:59.389Z",
        "orgId": "e51fbebd-6053-4e49-959f-1b94eeb69a2c",
        "shortName": "eclipse"
      },
      "references": [
        {
          "url": "https://gitlab.eclipse.org/security/cve-assignment/-/work_items/114"
        }
      ],
      "source": {
        "discovery": "UNKNOWN"
      },
      "x_generator": {
        "engine": "Vulnogram 1.0.2"
      }
    }
  },
  "cveMetadata": {
    "assignerOrgId": "e51fbebd-6053-4e49-959f-1b94eeb69a2c",
    "assignerShortName": "eclipse",
    "cveId": "CVE-2026-46580",
    "datePublished": "2026-06-18T14:26:59.389Z",
    "dateReserved": "2026-05-22T07:47:58.202Z",
    "dateUpdated": "2026-06-19T03:55:46.723Z",
    "state": "PUBLISHED"
  },
  "dataType": "CVE_RECORD",
  "dataVersion": "5.2"
}

CVE-2026-44717 (GCVE-0-2026-44717)

Vulnerability from cvelistv5 – Published: 2026-05-15 16:58 – Updated: 2026-05-15 17:25
VLAI
Title
MCP Calculate Server: Prompt Injection to RCE
Summary
MCP Calculate Server is a mathematical calculation service based on MCP protocol and SymPy library. Prior to 0.1.1, the use of eval() to evaluate mathematical expressions without proper input sanitization leads to remote code execution. This vulnerability is fixed in 0.1.1.
Severity
9.8 (Critical)
CVSS:3.1/AV:N/AC:L/PR:N/UI:N/S:U/C:H/I:H/A:H
SSVC
Exploitation: none Automatable: yes Technical Impact: total
CISA Coordinator · CISA-ADP (v2.0.3)
Decision recorded 2026-05-15 17:24 UTC
CWE
  • CWE-94 - Improper Control of Generation of Code ('Code Injection')
  • CWE-1427
Assigner
GitHub_M CNA
References
Impacted products
Show details on NVD website
To clipboard 

{
  "containers": {
    "adp": [
      {
        "metrics": [
          {
            "other": {
              "content": {
                "id": "CVE-2026-44717",
                "options": [
                  {
                    "Exploitation": "none"
                  },
                  {
                    "Automatable": "yes"
                  },
                  {
                    "Technical Impact": "total"
                  }
                ],
                "role": "CISA Coordinator",
                "timestamp": "2026-05-15T17:24:07.715411Z",
                "version": "2.0.3"
              },
              "type": "ssvc"
            }
          }
        ],
        "providerMetadata": {
          "dateUpdated": "2026-05-15T17:25:39.779Z",
          "orgId": "134c704f-9b21-4f2e-91b3-4a467353bcc0",
          "shortName": "CISA-ADP"
        },
        "title": "CISA ADP Vulnrichment"
      }
    ],
    "cna": {
      "affected": [
        {
          "product": "mcp_calculate_server",
          "vendor": "611711Dark",
          "versions": [
            {
              "status": "affected",
              "version": "\u003c 0.1.1"
            }
          ]
        }
      ],
      "descriptions": [
        {
          "lang": "en",
          "value": "MCP Calculate Server is a mathematical calculation service based on MCP protocol and SymPy library. Prior to 0.1.1, the use of eval() to evaluate mathematical expressions without proper input sanitization leads to remote code execution. This vulnerability is fixed in 0.1.1."
        }
      ],
      "metrics": [
        {
          "cvssV3_1": {
            "attackComplexity": "LOW",
            "attackVector": "NETWORK",
            "availabilityImpact": "HIGH",
            "baseScore": 9.8,
            "baseSeverity": "CRITICAL",
            "confidentialityImpact": "HIGH",
            "integrityImpact": "HIGH",
            "privilegesRequired": "NONE",
            "scope": "UNCHANGED",
            "userInteraction": "NONE",
            "vectorString": "CVSS:3.1/AV:N/AC:L/PR:N/UI:N/S:U/C:H/I:H/A:H",
            "version": "3.1"
          }
        }
      ],
      "problemTypes": [
        {
          "descriptions": [
            {
              "cweId": "CWE-94",
              "description": "CWE-94: Improper Control of Generation of Code (\u0027Code Injection\u0027)",
              "lang": "en",
              "type": "CWE"
            }
          ]
        },
        {
          "descriptions": [
            {
              "cweId": "CWE-1427",
              "description": "CWE-1427:",
              "lang": "en",
              "type": "CWE"
            }
          ]
        }
      ],
      "providerMetadata": {
        "dateUpdated": "2026-05-15T16:58:13.196Z",
        "orgId": "a0819718-46f1-4df5-94e2-005712e83aaa",
        "shortName": "GitHub_M"
      },
      "references": [
        {
          "name": "https://github.com/611711Dark/mcp_calculate_server/security/advisories/GHSA-2mgq-7rfg-rwpj",
          "tags": [
            "x_refsource_CONFIRM"
          ],
          "url": "https://github.com/611711Dark/mcp_calculate_server/security/advisories/GHSA-2mgq-7rfg-rwpj"
        }
      ],
      "source": {
        "advisory": "GHSA-2mgq-7rfg-rwpj",
        "discovery": "UNKNOWN"
      },
      "title": "MCP Calculate Server: Prompt Injection to RCE"
    }
  },
  "cveMetadata": {
    "assignerOrgId": "a0819718-46f1-4df5-94e2-005712e83aaa",
    "assignerShortName": "GitHub_M",
    "cveId": "CVE-2026-44717",
    "datePublished": "2026-05-15T16:58:13.196Z",
    "dateReserved": "2026-05-07T18:04:17.307Z",
    "dateUpdated": "2026-05-15T17:25:39.779Z",
    "state": "PUBLISHED"
  },
  "dataType": "CVE_RECORD",
  "dataVersion": "5.2"
}

CVE-2026-44688 (GCVE-0-2026-44688)

Vulnerability from cvelistv5 – Published: 2026-06-18 14:22 – Updated: 2026-06-19 03:55
VLAI
Summary
In Eclipse Theia versions prior to 1.71.0, the AI chat agent processed workspace file and directory names as part of its prompt context without distinguishing them from system instructions. An attacker could craft a malicious repository with adversarial directory or file names that, when analyzed by the AI agent, would cause the agent to follow attacker-controlled instructions (indirect prompt injection). Combined with other AI chat features available in untrusted workspaces, this enabled attack chains leading to data exfiltration via Markdown image rendering or arbitrary command execution via task definitions.
Severity
8.4 (High)
CVSS:4.0/AV:L/AC:L/AT:N/PR:N/UI:A/VC:H/VI:H/VA:H/SC:N/SI:N/SA:N
SSVC
Exploitation: none Automatable: no Technical Impact: total
CISA Coordinator · CISA-ADP (v2.0.3)
Decision recorded 2026-06-18 00:00 UTC
CWE
  • CWE-1427 - Improper neutralization of input used for LLM prompting
  • CWE-829 - Inclusion of functionality from untrusted control sphere
Assigner
eclipse CNA
References
Impacted products
Vendor Product Version
Eclipse Foundation Eclipse Theia Affected: 0 , < 1.71.0 (semver)
Create a notification for this product.
Credits
Piotr Ryciak (https://gitlab.eclipse.org/void01)
Show details on NVD website
To clipboard 

{
  "containers": {
    "adp": [
      {
        "metrics": [
          {
            "other": {
              "content": {
                "id": "CVE-2026-44688",
                "options": [
                  {
                    "Exploitation": "none"
                  },
                  {
                    "Automatable": "no"
                  },
                  {
                    "Technical Impact": "total"
                  }
                ],
                "role": "CISA Coordinator",
                "timestamp": "2026-06-18T00:00:00+00:00",
                "version": "2.0.3"
              },
              "type": "ssvc"
            }
          }
        ],
        "providerMetadata": {
          "dateUpdated": "2026-06-19T03:55:47.810Z",
          "orgId": "134c704f-9b21-4f2e-91b3-4a467353bcc0",
          "shortName": "CISA-ADP"
        },
        "title": "CISA ADP Vulnrichment"
      }
    ],
    "cna": {
      "affected": [
        {
          "defaultStatus": "unaffected",
          "product": "Eclipse Theia",
          "repo": "https://github.com/eclipse-theia/theia",
          "vendor": "Eclipse Foundation",
          "versions": [
            {
              "lessThan": "1.71.0",
              "status": "affected",
              "version": "0",
              "versionType": "semver"
            }
          ]
        }
      ],
      "credits": [
        {
          "lang": "en",
          "type": "finder",
          "value": "Piotr Ryciak (https://gitlab.eclipse.org/void01)"
        }
      ],
      "descriptions": [
        {
          "lang": "en",
          "supportingMedia": [
            {
              "base64": false,
              "type": "text/html",
              "value": "In Eclipse Theia versions prior to 1.71.0, the AI chat agent processed workspace file and directory names as part of its prompt context without distinguishing them from system instructions. An attacker could craft a malicious repository with adversarial directory or file names that, when analyzed by the AI agent, would cause the agent to follow attacker-controlled instructions (indirect prompt injection). Combined with other AI chat features available in untrusted workspaces, this enabled attack chains leading to data exfiltration via Markdown image rendering or arbitrary command execution via task definitions."
            }
          ],
          "value": "In Eclipse Theia versions prior to 1.71.0, the AI chat agent processed workspace file and directory names as part of its prompt context without distinguishing them from system instructions. An attacker could craft a malicious repository with adversarial directory or file names that, when analyzed by the AI agent, would cause the agent to follow attacker-controlled instructions (indirect prompt injection). Combined with other AI chat features available in untrusted workspaces, this enabled attack chains leading to data exfiltration via Markdown image rendering or arbitrary command execution via task definitions."
        }
      ],
      "metrics": [
        {
          "cvssV4_0": {
            "Automatable": "NOT_DEFINED",
            "Recovery": "NOT_DEFINED",
            "Safety": "NOT_DEFINED",
            "attackComplexity": "LOW",
            "attackRequirements": "NONE",
            "attackVector": "LOCAL",
            "baseScore": 8.4,
            "baseSeverity": "HIGH",
            "exploitMaturity": "NOT_DEFINED",
            "privilegesRequired": "NONE",
            "providerUrgency": "NOT_DEFINED",
            "subAvailabilityImpact": "NONE",
            "subConfidentialityImpact": "NONE",
            "subIntegrityImpact": "NONE",
            "userInteraction": "ACTIVE",
            "valueDensity": "NOT_DEFINED",
            "vectorString": "CVSS:4.0/AV:L/AC:L/AT:N/PR:N/UI:A/VC:H/VI:H/VA:H/SC:N/SI:N/SA:N",
            "version": "4.0",
            "vulnAvailabilityImpact": "HIGH",
            "vulnConfidentialityImpact": "HIGH",
            "vulnIntegrityImpact": "HIGH",
            "vulnerabilityResponseEffort": "NOT_DEFINED"
          },
          "format": "CVSS",
          "scenarios": [
            {
              "lang": "en",
              "value": "GENERAL"
            }
          ]
        }
      ],
      "problemTypes": [
        {
          "descriptions": [
            {
              "cweId": "CWE-1427",
              "description": "CWE-1427 Improper neutralization of input used for LLM prompting",
              "lang": "en",
              "type": "CWE"
            }
          ]
        },
        {
          "descriptions": [
            {
              "cweId": "CWE-829",
              "description": "CWE-829 Inclusion of functionality from untrusted control sphere",
              "lang": "en",
              "type": "CWE"
            }
          ]
        }
      ],
      "providerMetadata": {
        "dateUpdated": "2026-06-18T14:22:33.738Z",
        "orgId": "e51fbebd-6053-4e49-959f-1b94eeb69a2c",
        "shortName": "eclipse"
      },
      "references": [
        {
          "url": "https://gitlab.eclipse.org/security/cve-assignment/-/work_items/113"
        }
      ],
      "source": {
        "discovery": "UNKNOWN"
      },
      "x_generator": {
        "engine": "Vulnogram 1.0.2"
      }
    }
  },
  "cveMetadata": {
    "assignerOrgId": "e51fbebd-6053-4e49-959f-1b94eeb69a2c",
    "assignerShortName": "eclipse",
    "cveId": "CVE-2026-44688",
    "datePublished": "2026-06-18T14:22:33.738Z",
    "dateReserved": "2026-05-22T07:47:58.196Z",
    "dateUpdated": "2026-06-19T03:55:47.810Z",
    "state": "PUBLISHED"
  },
  "dataType": "CVE_RECORD",
  "dataVersion": "5.2"
}

CVE-2026-44246 (GCVE-0-2026-44246)

Vulnerability from cvelistv5 – Published: 2026-05-12 20:41 – Updated: 2026-05-13 14:23
VLAI
Title
nnU-Net: Agentic workflow injection in `.github/workflows/issue-triage.yml` of `MIC-DKFZ/nnUNet`
Summary
nnU-Net is a semantic segmentation framework that automatically adapts its pipeline to a dataset. Prior to 2.4.1, the nnU-Net Issue Triage workflow in .github/workflows/issue-triage.yml is vulnerable to Agentic Workflow Injection. The workflow sets allowed_non_write_users: ${{ github.event.issue.user.login }}, which means any logged-in GitHub user who opens an issue can reach this agentic workflow with attacker-controlled content. Untrusted issue title and body content are embedded directly into the prompt of anthropics/claude-code-action, and the workflow then runs a command-capable Claude agent with permission to comment on and relabel the current issue via gh. Because this workflow is triggered automatically on issues.opened, an external attacker can submit a crafted issue that steers the agent beyond its intended issue-triage purpose and influences authenticated issue actions. This vulnerability is fixed in 2.4.1.
Severity
7.2 (High)
CVSS:3.1/AV:N/AC:L/PR:N/UI:N/S:C/C:L/I:L/A:N
SSVC
Exploitation: poc Automatable: yes Technical Impact: partial
CISA Coordinator · CISA-ADP (v2.0.3)
Decision recorded 2026-05-13 14:23 UTC
CWE
Assigner
GitHub_M CNA
References
Impacted products
Vendor Product Version
MIC-DKFZ nnUNet Affected: < 2.4.1
Create a notification for this product.
Show details on NVD website
To clipboard 

{
  "containers": {
    "adp": [
      {
        "metrics": [
          {
            "other": {
              "content": {
                "id": "CVE-2026-44246",
                "options": [
                  {
                    "Exploitation": "poc"
                  },
                  {
                    "Automatable": "yes"
                  },
                  {
                    "Technical Impact": "partial"
                  }
                ],
                "role": "CISA Coordinator",
                "timestamp": "2026-05-13T14:23:08.264352Z",
                "version": "2.0.3"
              },
              "type": "ssvc"
            }
          }
        ],
        "providerMetadata": {
          "dateUpdated": "2026-05-13T14:23:29.727Z",
          "orgId": "134c704f-9b21-4f2e-91b3-4a467353bcc0",
          "shortName": "CISA-ADP"
        },
        "references": [
          {
            "tags": [
              "exploit"
            ],
            "url": "https://github.com/MIC-DKFZ/nnUNet/security/advisories/GHSA-63mx-j37w-gh59"
          }
        ],
        "title": "CISA ADP Vulnrichment"
      }
    ],
    "cna": {
      "affected": [
        {
          "product": "nnUNet",
          "vendor": "MIC-DKFZ",
          "versions": [
            {
              "status": "affected",
              "version": "\u003c 2.4.1"
            }
          ]
        }
      ],
      "descriptions": [
        {
          "lang": "en",
          "value": "nnU-Net is a semantic segmentation framework that automatically adapts its pipeline to a dataset. Prior to 2.4.1, the nnU-Net Issue Triage workflow in .github/workflows/issue-triage.yml is vulnerable to Agentic Workflow Injection. The workflow sets allowed_non_write_users: ${{ github.event.issue.user.login }}, which means any logged-in GitHub user who opens an issue can reach this agentic workflow with attacker-controlled content. Untrusted issue title and body content are embedded directly into the prompt of anthropics/claude-code-action, and the workflow then runs a command-capable Claude agent with permission to comment on and relabel the current issue via gh. Because this workflow is triggered automatically on issues.opened, an external attacker can submit a crafted issue that steers the agent beyond its intended issue-triage purpose and influences authenticated issue actions. This vulnerability is fixed in 2.4.1."
        }
      ],
      "metrics": [
        {
          "cvssV3_1": {
            "attackComplexity": "LOW",
            "attackVector": "NETWORK",
            "availabilityImpact": "NONE",
            "baseScore": 7.2,
            "baseSeverity": "HIGH",
            "confidentialityImpact": "LOW",
            "integrityImpact": "LOW",
            "privilegesRequired": "NONE",
            "scope": "CHANGED",
            "userInteraction": "NONE",
            "vectorString": "CVSS:3.1/AV:N/AC:L/PR:N/UI:N/S:C/C:L/I:L/A:N",
            "version": "3.1"
          }
        }
      ],
      "problemTypes": [
        {
          "descriptions": [
            {
              "cweId": "CWE-1427",
              "description": "CWE-1427:",
              "lang": "en",
              "type": "CWE"
            }
          ]
        }
      ],
      "providerMetadata": {
        "dateUpdated": "2026-05-12T20:41:32.162Z",
        "orgId": "a0819718-46f1-4df5-94e2-005712e83aaa",
        "shortName": "GitHub_M"
      },
      "references": [
        {
          "name": "https://github.com/MIC-DKFZ/nnUNet/security/advisories/GHSA-63mx-j37w-gh59",
          "tags": [
            "x_refsource_CONFIRM"
          ],
          "url": "https://github.com/MIC-DKFZ/nnUNet/security/advisories/GHSA-63mx-j37w-gh59"
        }
      ],
      "source": {
        "advisory": "GHSA-63mx-j37w-gh59",
        "discovery": "UNKNOWN"
      },
      "title": "nnU-Net: Agentic workflow injection in `.github/workflows/issue-triage.yml` of `MIC-DKFZ/nnUNet`"
    }
  },
  "cveMetadata": {
    "assignerOrgId": "a0819718-46f1-4df5-94e2-005712e83aaa",
    "assignerShortName": "GitHub_M",
    "cveId": "CVE-2026-44246",
    "datePublished": "2026-05-12T20:41:32.162Z",
    "dateReserved": "2026-05-05T16:33:55.844Z",
    "dateUpdated": "2026-05-13T14:23:29.727Z",
    "state": "PUBLISHED"
  },
  "dataType": "CVE_RECORD",
  "dataVersion": "5.2"
}

CVE-2026-21832 (GCVE-0-2026-21832)

Vulnerability from cvelistv5 – Published: 2026-08-13 13:24 – Updated: 2026-08-13 15:51
VLAI
Title
HCL AION is affected by multiple security vulnerabilities.
Summary
HCL AION is affected by a vulnerability where indirect prompt injection can lead to HTML injection in rendered output. Injected markup may be displayed to users, potentially resulting in unintended behavior or security impact under certain conditions.
Severity
4.3 (Medium)
CVSS:3.1/AV:N/AC:L/PR:L/UI:N/S:U/C:L/I:N/A:N
SSVC
Exploitation: none Automatable: no Technical Impact: partial
CISA Coordinator · CISA-ADP (v2.0.3)
Decision recorded 2026-08-13 15:51 UTC
CWE
  • CWE-1427 - Improper Neutralization of Input Used for LLM Prompting
Assigner
HCL CNA
References
Impacted products
Vendor Product Version
HCL Software AION Affected: v2.5.0
Create a notification for this product.
Show details on NVD website
To clipboard 

{
  "containers": {
    "adp": [
      {
        "metrics": [
          {
            "other": {
              "content": {
                "id": "CVE-2026-21832",
                "options": [
                  {
                    "Exploitation": "none"
                  },
                  {
                    "Automatable": "no"
                  },
                  {
                    "Technical Impact": "partial"
                  }
                ],
                "role": "CISA Coordinator",
                "timestamp": "2026-08-13T15:51:06.260012Z",
                "version": "2.0.3"
              },
              "type": "ssvc"
            }
          }
        ],
        "providerMetadata": {
          "dateUpdated": "2026-08-13T15:51:19.817Z",
          "orgId": "134c704f-9b21-4f2e-91b3-4a467353bcc0",
          "shortName": "CISA-ADP"
        },
        "title": "CISA ADP Vulnrichment"
      }
    ],
    "cna": {
      "affected": [
        {
          "defaultStatus": "unaffected",
          "product": "AION",
          "vendor": "HCL Software",
          "versions": [
            {
              "status": "affected",
              "version": "v2.5.0"
            }
          ]
        }
      ],
      "descriptions": [
        {
          "lang": "en",
          "supportingMedia": [
            {
              "base64": false,
              "type": "text/html",
              "value": "HCL AION is affected by a vulnerability where indirect prompt injection can lead to HTML injection in rendered output. Injected markup may be displayed to users, potentially resulting in unintended behavior or security impact under certain conditions."
            }
          ],
          "value": "HCL AION is affected by a vulnerability where indirect prompt injection can lead to HTML injection in rendered output. Injected markup may be displayed to users, potentially resulting in unintended behavior or security impact under certain conditions."
        }
      ],
      "metrics": [
        {
          "cvssV3_1": {
            "attackComplexity": "LOW",
            "attackVector": "NETWORK",
            "availabilityImpact": "NONE",
            "baseScore": 4.3,
            "baseSeverity": "MEDIUM",
            "confidentialityImpact": "LOW",
            "integrityImpact": "NONE",
            "privilegesRequired": "LOW",
            "scope": "UNCHANGED",
            "userInteraction": "NONE",
            "vectorString": "CVSS:3.1/AV:N/AC:L/PR:L/UI:N/S:U/C:L/I:N/A:N",
            "version": "3.1"
          },
          "format": "CVSS",
          "scenarios": [
            {
              "lang": "en",
              "value": "GENERAL"
            }
          ]
        }
      ],
      "problemTypes": [
        {
          "descriptions": [
            {
              "cweId": "CWE-1427",
              "description": "CWE-1427 Improper Neutralization of Input Used for LLM Prompting",
              "lang": "en",
              "type": "CWE"
            }
          ]
        }
      ],
      "providerMetadata": {
        "dateUpdated": "2026-08-13T13:24:30.086Z",
        "orgId": "1e47fe04-f25f-42fa-b674-36de2c5e3cfc",
        "shortName": "HCL"
      },
      "references": [
        {
          "url": "https://support.hcl-software.com/csm?id=kb_article\u0026sysparm_article=KB0133084"
        }
      ],
      "source": {
        "discovery": "UNKNOWN"
      },
      "title": "HCL AION is affected by multiple security vulnerabilities.",
      "x_generator": {
        "engine": "Vulnogram 1.0.0"
      }
    }
  },
  "cveMetadata": {
    "assignerOrgId": "1e47fe04-f25f-42fa-b674-36de2c5e3cfc",
    "assignerShortName": "HCL",
    "cveId": "CVE-2026-21832",
    "datePublished": "2026-08-13T13:24:30.086Z",
    "dateReserved": "2026-01-05T16:08:25.000Z",
    "dateUpdated": "2026-08-13T15:51:19.817Z",
    "state": "PUBLISHED"
  },
  "dataType": "CVE_RECORD",
  "dataVersion": "5.2"
}

CVE-2026-18733 (GCVE-0-2026-18733)

Vulnerability from cvelistv5 – Published: 2026-08-03 20:33 – Updated: 2026-08-04 19:31
VLAI
Title
Prompt injection bypasses shell tool consent gate in Strands Agents Tools
Summary
A prompt injection vulnerability in the shell tool in Amazon Strands Agents Tools before 0.8.0 might allow remote actors to execute arbitrary operating system commands on the agent's host via a crafted prompt that sets the non_interactive parameter to true, bypassing the human consent gate. To remediate this issue, users should upgrade to version 0.8.0.
Severity
8.8 (High)
CVSS:3.1/AV:N/AC:L/PR:N/UI:R/S:U/C:H/I:H/A:H
7.5 (High)
CVSS:4.0/AV:N/AC:L/AT:P/PR:N/UI:A/VC:H/VI:H/VA:H/SC:N/SI:N/SA:N
SSVC
Exploitation: none Automatable: no Technical Impact: total
CISA Coordinator · CISA-ADP (v2.0.3)
Decision recorded 2026-08-04 19:31 UTC
CWE
  • CWE-1427 - Improper neutralization of input used for LLM prompting
Assigner
AMZN CNA
References
Impacted products
Vendor Product Version
AWS strands-agents-tools Affected: 0 , < 0.8.0 (custom)
    cpe:2.3:a:aws:strands-agents-tools:*:*:*:*:*:*:*:*
Create a notification for this product.
Show details on NVD website
To clipboard 

{
  "containers": {
    "adp": [
      {
        "metrics": [
          {
            "other": {
              "content": {
                "id": "CVE-2026-18733",
                "options": [
                  {
                    "Exploitation": "none"
                  },
                  {
                    "Automatable": "no"
                  },
                  {
                    "Technical Impact": "total"
                  }
                ],
                "role": "CISA Coordinator",
                "timestamp": "2026-08-04T19:31:10.408324Z",
                "version": "2.0.3"
              },
              "type": "ssvc"
            }
          }
        ],
        "providerMetadata": {
          "dateUpdated": "2026-08-04T19:31:53.415Z",
          "orgId": "134c704f-9b21-4f2e-91b3-4a467353bcc0",
          "shortName": "CISA-ADP"
        },
        "title": "CISA ADP Vulnrichment"
      }
    ],
    "cna": {
      "affected": [
        {
          "defaultStatus": "unaffected",
          "product": "strands-agents-tools",
          "vendor": "AWS",
          "versions": [
            {
              "lessThan": "0.8.0",
              "status": "affected",
              "version": "0",
              "versionType": "custom"
            }
          ]
        }
      ],
      "cpeApplicability": [
        {
          "nodes": [
            {
              "cpeMatch": [
                {
                  "criteria": "cpe:2.3:a:aws:strands-agents-tools:*:*:*:*:*:*:*:*",
                  "versionEndExcluding": "0.8.0",
                  "versionStartIncluding": "0",
                  "vulnerable": true
                }
              ],
              "negate": false,
              "operator": "OR"
            }
          ],
          "operator": "OR"
        }
      ],
      "descriptions": [
        {
          "lang": "en",
          "supportingMedia": [
            {
              "base64": false,
              "type": "text/html",
              "value": "\u003cp\u003eA prompt injection vulnerability in the shell tool in Amazon Strands Agents Tools before 0.8.0 might allow remote actors to execute arbitrary operating system commands on the agent\u0027s host via a crafted prompt that sets the non_interactive parameter to true, bypassing the human consent gate.\u003c/p\u003e\u003cp\u003eTo remediate this issue, users should upgrade to version 0.8.0.\u003c/p\u003e"
            }
          ],
          "value": "A prompt injection vulnerability in the shell tool in Amazon Strands Agents Tools before 0.8.0 might allow remote actors to execute arbitrary operating system commands on the agent\u0027s host via a crafted prompt that sets the non_interactive parameter to true, bypassing the human consent gate.\n\n\n\nTo remediate this issue, users should upgrade to version 0.8.0."
        }
      ],
      "impacts": [
        {
          "capecId": "CAPEC-248",
          "descriptions": [
            {
              "lang": "en",
              "value": "CAPEC-248 Command Injection"
            }
          ]
        }
      ],
      "metrics": [
        {
          "cvssV3_1": {
            "attackComplexity": "LOW",
            "attackVector": "NETWORK",
            "availabilityImpact": "HIGH",
            "baseScore": 8.8,
            "baseSeverity": "HIGH",
            "confidentialityImpact": "HIGH",
            "integrityImpact": "HIGH",
            "privilegesRequired": "NONE",
            "scope": "UNCHANGED",
            "userInteraction": "REQUIRED",
            "vectorString": "CVSS:3.1/AV:N/AC:L/PR:N/UI:R/S:U/C:H/I:H/A:H",
            "version": "3.1"
          },
          "format": "CVSS",
          "scenarios": [
            {
              "lang": "en",
              "value": "GENERAL"
            }
          ]
        },
        {
          "cvssV4_0": {
            "Automatable": "NOT_DEFINED",
            "Recovery": "NOT_DEFINED",
            "Safety": "NOT_DEFINED",
            "attackComplexity": "LOW",
            "attackRequirements": "PRESENT",
            "attackVector": "NETWORK",
            "baseScore": 7.5,
            "baseSeverity": "HIGH",
            "exploitMaturity": "NOT_DEFINED",
            "privilegesRequired": "NONE",
            "providerUrgency": "NOT_DEFINED",
            "subAvailabilityImpact": "NONE",
            "subConfidentialityImpact": "NONE",
            "subIntegrityImpact": "NONE",
            "userInteraction": "ACTIVE",
            "valueDensity": "NOT_DEFINED",
            "vectorString": "CVSS:4.0/AV:N/AC:L/AT:P/PR:N/UI:A/VC:H/VI:H/VA:H/SC:N/SI:N/SA:N",
            "version": "4.0",
            "vulnAvailabilityImpact": "HIGH",
            "vulnConfidentialityImpact": "HIGH",
            "vulnIntegrityImpact": "HIGH",
            "vulnerabilityResponseEffort": "NOT_DEFINED"
          },
          "format": "CVSS",
          "scenarios": [
            {
              "lang": "en",
              "value": "GENERAL"
            }
          ]
        }
      ],
      "problemTypes": [
        {
          "descriptions": [
            {
              "cweId": "CWE-1427",
              "description": "CWE-1427 Improper neutralization of input used for LLM prompting",
              "lang": "en",
              "type": "CWE"
            }
          ]
        }
      ],
      "providerMetadata": {
        "dateUpdated": "2026-08-03T20:35:23.023Z",
        "orgId": "ff89ba41-3aa1-4d27-914a-91399e9639e5",
        "shortName": "AMZN"
      },
      "references": [
        {
          "tags": [
            "release-notes",
            "patch"
          ],
          "url": "https://pypi.org/project/strands-agents-tools/0.8.0/"
        },
        {
          "tags": [
            "vendor-advisory"
          ],
          "url": "https://aws.amazon.com/security/security-bulletins/2026-072-aws/"
        },
        {
          "tags": [
            "release-notes"
          ],
          "url": "https://github.com/strands-agents/tools/security/advisories/GHSA-mqvc-p852-wf8x"
        }
      ],
      "source": {
        "discovery": "UNKNOWN"
      },
      "title": "Prompt injection bypasses shell tool consent gate in Strands Agents Tools",
      "x_generator": {
        "engine": "Vulnogram 1.0.4"
      }
    }
  },
  "cveMetadata": {
    "assignerOrgId": "ff89ba41-3aa1-4d27-914a-91399e9639e5",
    "assignerShortName": "AMZN",
    "cveId": "CVE-2026-18733",
    "datePublished": "2026-08-03T20:33:24.872Z",
    "dateReserved": "2026-08-03T18:48:48.218Z",
    "dateUpdated": "2026-08-04T19:31:53.415Z",
    "state": "PUBLISHED"
  },
  "dataType": "CVE_RECORD",
  "dataVersion": "5.2"
}
Mitigation
Architecture and Design

LLM-enabled applications should be designed to ensure proper sanitization of user-controllable input, ensuring that no intentionally misleading or dangerous characters can be included. Additionally, they should be designed in a way that ensures that user-controllable input is identified as untrusted and potentially dangerous.

Mitigation
Implementation

LLM prompts should be constructed in a way that effectively differentiates between user-supplied input and developer-constructed system prompting to reduce the chance of model confusion at inference-time.

Mitigation
Architecture and Design

LLM-enabled applications should be designed to ensure proper sanitization of user-controllable input, ensuring that no intentionally misleading or dangerous characters can be included. Additionally, they should be designed in a way that ensures that user-controllable input is identified as untrusted and potentially dangerous.

Mitigation
Implementation

Ensure that model training includes training examples that avoid leaking secrets and disregard malicious inputs. Train the model to recognize secrets, and label training data appropriately. Note that due to the non-deterministic nature of prompting LLMs, it is necessary to perform testing of the same test case several times in order to ensure that troublesome behavior is not possible. Additionally, testing should be performed each time a new model is used or a model's weights are updated.

Mitigation
Installation Operation

During deployment/operation, use components that operate externally to the system to monitor the output and act as a moderator. These components are called different terms, such as supervisors or guardrails.

Mitigation
System Configuration

During system configuration, the model could be fine-tuned to better control and neutralize potentially dangerous inputs.

No CAPEC attack patterns related to this CWE.

← Back to the CWE list