CVE-2026-70477 (GCVE-0-2026-70477)
Vulnerability from cvelistv5
Published
2026-08-04 19:29
Modified
2026-08-05 13:51
Severity ?
9.5 (Critical) - CVSS:4.0/AV:N/AC:H/AT:P/PR:N/UI:N/VC:H/VI:H/VA:H/SC:H/SI:H/SA:H
CWE
  • CWE-94 - Improper Control of Generation of Code ('Code Injection')
Summary
Flowise is a drag & drop user interface to build a customized large language model flow. Prior to 3.1.3, a prompt injection sent to a chatflow using a CSV Agent node can cause the LLM to respond with a malicious Python script that bypasses the blocklist validator and executes in an unsandboxed Pyodide environment. The specific flaw exists within the run method of the CSV_Agents class, where untrusted data is used to construct an LLM prompt and the resulting pythonCode is validated by validatePythonCodeForDataFrame before execution. An attacker can leverage this to execute arbitrary code in the context of the service account. This issue is fixed in 3.1.3.
References
Impacted products
Vendor Product Version
FlowiseAI Flowise Version: < 3.1.2
 Create a notification for this product.
Show details on NVD website

To clipboard 

{
  "containers": {
    "adp": [
      {
        "metrics": [
          {
            "other": {
              "content": {
                "id": "CVE-2026-70477",
                "options": [
                  {
                    "Exploitation": "poc"
                  },
                  {
                    "Automatable": "yes"
                  },
                  {
                    "Technical Impact": "total"
                  }
                ],
                "role": "CISA Coordinator",
                "timestamp": "2026-08-05T13:51:06.061832Z",
                "version": "2.0.3"
              },
              "type": "ssvc"
            }
          }
        ],
        "providerMetadata": {
          "dateUpdated": "2026-08-05T13:51:57.817Z",
          "orgId": "134c704f-9b21-4f2e-91b3-4a467353bcc0",
          "shortName": "CISA-ADP"
        },
        "references": [
          {
            "tags": [
              "exploit"
            ],
            "url": "https://github.com/FlowiseAI/Flowise/security/advisories/GHSA-5xvg-pmgg-3mxr"
          }
        ],
        "title": "CISA ADP Vulnrichment"
      }
    ],
    "cna": {
      "affected": [
        {
          "product": "Flowise",
          "vendor": "FlowiseAI",
          "versions": [
            {
              "status": "affected",
              "version": "\u003c 3.1.2"
            }
          ]
        }
      ],
      "descriptions": [
        {
          "lang": "en",
          "value": "Flowise is a drag \u0026 drop user interface to build a customized large language model flow. Prior to 3.1.3, a prompt injection sent to a chatflow using a CSV Agent node can cause the LLM to respond with a malicious Python script that bypasses the blocklist validator and executes in an unsandboxed Pyodide environment. The specific flaw exists within the run method of the CSV_Agents class, where untrusted data is used to construct an LLM prompt and the resulting pythonCode is validated by validatePythonCodeForDataFrame before execution. An attacker can leverage this to execute arbitrary code in the context of the service account. This issue is fixed in 3.1.3."
        }
      ],
      "metrics": [
        {
          "cvssV4_0": {
            "attackComplexity": "HIGH",
            "attackRequirements": "PRESENT",
            "attackVector": "NETWORK",
            "baseScore": 9.5,
            "baseSeverity": "CRITICAL",
            "privilegesRequired": "NONE",
            "subAvailabilityImpact": "HIGH",
            "subConfidentialityImpact": "HIGH",
            "subIntegrityImpact": "HIGH",
            "userInteraction": "NONE",
            "vectorString": "CVSS:4.0/AV:N/AC:H/AT:P/PR:N/UI:N/VC:H/VI:H/VA:H/SC:H/SI:H/SA:H",
            "version": "4.0",
            "vulnAvailabilityImpact": "HIGH",
            "vulnConfidentialityImpact": "HIGH",
            "vulnIntegrityImpact": "HIGH"
          }
        }
      ],
      "problemTypes": [
        {
          "descriptions": [
            {
              "cweId": "CWE-94",
              "description": "CWE-94: Improper Control of Generation of Code (\u0027Code Injection\u0027)",
              "lang": "en",
              "type": "CWE"
            }
          ]
        }
      ],
      "providerMetadata": {
        "dateUpdated": "2026-08-04T19:29:14.796Z",
        "orgId": "a0819718-46f1-4df5-94e2-005712e83aaa",
        "shortName": "GitHub_M"
      },
      "references": [
        {
          "name": "https://github.com/FlowiseAI/Flowise/security/advisories/GHSA-5xvg-pmgg-3mxr",
          "tags": [
            "x_refsource_CONFIRM"
          ],
          "url": "https://github.com/FlowiseAI/Flowise/security/advisories/GHSA-5xvg-pmgg-3mxr"
        },
        {
          "name": "https://github.com/FlowiseAI/Flowise/pull/6499",
          "tags": [
            "x_refsource_MISC"
          ],
          "url": "https://github.com/FlowiseAI/Flowise/pull/6499"
        },
        {
          "name": "https://github.com/FlowiseAI/Flowise/commit/f4e2794f6a576b94578f2fdafbf49c2fb304626c",
          "tags": [
            "x_refsource_MISC"
          ],
          "url": "https://github.com/FlowiseAI/Flowise/commit/f4e2794f6a576b94578f2fdafbf49c2fb304626c"
        },
        {
          "name": "https://github.com/FlowiseAI/Flowise/releases/tag/flowise@3.1.3",
          "tags": [
            "x_refsource_MISC"
          ],
          "url": "https://github.com/FlowiseAI/Flowise/releases/tag/flowise@3.1.3"
        }
      ],
      "source": {
        "advisory": "GHSA-5xvg-pmgg-3mxr",
        "discovery": "UNKNOWN"
      },
      "title": "Flowise: CSV Agent Prompt Injection Remote Code Execution Vulnerability"
    }
  },
  "cveMetadata": {
    "assignerOrgId": "a0819718-46f1-4df5-94e2-005712e83aaa",
    "assignerShortName": "GitHub_M",
    "cveId": "CVE-2026-70477",
    "datePublished": "2026-08-04T19:29:14.796Z",
    "dateReserved": "2026-08-04T15:24:41.339Z",
    "dateUpdated": "2026-08-05T13:51:57.817Z",
    "state": "PUBLISHED"
  },
  "dataType": "CVE_RECORD",
  "dataVersion": "5.2",
  "vulnerability-lookup:meta": {
    "vulnrichment": {
      "containers": "{\"adp\": [{\"title\": \"CISA ADP Vulnrichment\", \"metrics\": [{\"other\": {\"type\": \"ssvc\", \"content\": {\"id\": \"CVE-2026-70477\", \"role\": \"CISA Coordinator\", \"options\": [{\"Exploitation\": \"poc\"}, {\"Automatable\": \"yes\"}, {\"Technical Impact\": \"total\"}], \"version\": \"2.0.3\", \"timestamp\": \"2026-08-05T13:51:06.061832Z\"}}}], \"references\": [{\"url\": \"https://github.com/FlowiseAI/Flowise/security/advisories/GHSA-5xvg-pmgg-3mxr\", \"tags\": [\"exploit\"]}], \"providerMetadata\": {\"orgId\": \"134c704f-9b21-4f2e-91b3-4a467353bcc0\", \"shortName\": \"CISA-ADP\", \"dateUpdated\": \"2026-08-05T13:51:30.332Z\"}}], \"cna\": {\"title\": \"Flowise: CSV Agent Prompt Injection Remote Code Execution Vulnerability\", \"source\": {\"advisory\": \"GHSA-5xvg-pmgg-3mxr\", \"discovery\": \"UNKNOWN\"}, \"metrics\": [{\"cvssV4_0\": {\"version\": \"4.0\", \"baseScore\": 9.5, \"attackVector\": \"NETWORK\", \"baseSeverity\": \"CRITICAL\", \"vectorString\": \"CVSS:4.0/AV:N/AC:H/AT:P/PR:N/UI:N/VC:H/VI:H/VA:H/SC:H/SI:H/SA:H\", \"userInteraction\": \"NONE\", \"attackComplexity\": \"HIGH\", \"attackRequirements\": \"PRESENT\", \"privilegesRequired\": \"NONE\", \"subIntegrityImpact\": \"HIGH\", \"vulnIntegrityImpact\": \"HIGH\", \"subAvailabilityImpact\": \"HIGH\", \"vulnAvailabilityImpact\": \"HIGH\", \"subConfidentialityImpact\": \"HIGH\", \"vulnConfidentialityImpact\": \"HIGH\"}}], \"affected\": [{\"vendor\": \"FlowiseAI\", \"product\": \"Flowise\", \"versions\": [{\"status\": \"affected\", \"version\": \"\u003c 3.1.2\"}]}], \"references\": [{\"url\": \"https://github.com/FlowiseAI/Flowise/security/advisories/GHSA-5xvg-pmgg-3mxr\", \"name\": \"https://github.com/FlowiseAI/Flowise/security/advisories/GHSA-5xvg-pmgg-3mxr\", \"tags\": [\"x_refsource_CONFIRM\"]}, {\"url\": \"https://github.com/FlowiseAI/Flowise/pull/6499\", \"name\": \"https://github.com/FlowiseAI/Flowise/pull/6499\", \"tags\": [\"x_refsource_MISC\"]}, {\"url\": \"https://github.com/FlowiseAI/Flowise/commit/f4e2794f6a576b94578f2fdafbf49c2fb304626c\", \"name\": \"https://github.com/FlowiseAI/Flowise/commit/f4e2794f6a576b94578f2fdafbf49c2fb304626c\", \"tags\": [\"x_refsource_MISC\"]}, {\"url\": \"https://github.com/FlowiseAI/Flowise/releases/tag/flowise@3.1.3\", \"name\": \"https://github.com/FlowiseAI/Flowise/releases/tag/flowise@3.1.3\", \"tags\": [\"x_refsource_MISC\"]}], \"descriptions\": [{\"lang\": \"en\", \"value\": \"Flowise is a drag \u0026 drop user interface to build a customized large language model flow. Prior to 3.1.3, a prompt injection sent to a chatflow using a CSV Agent node can cause the LLM to respond with a malicious Python script that bypasses the blocklist validator and executes in an unsandboxed Pyodide environment. The specific flaw exists within the run method of the CSV_Agents class, where untrusted data is used to construct an LLM prompt and the resulting pythonCode is validated by validatePythonCodeForDataFrame before execution. An attacker can leverage this to execute arbitrary code in the context of the service account. This issue is fixed in 3.1.3.\"}], \"problemTypes\": [{\"descriptions\": [{\"lang\": \"en\", \"type\": \"CWE\", \"cweId\": \"CWE-94\", \"description\": \"CWE-94: Improper Control of Generation of Code (\u0027Code Injection\u0027)\"}]}], \"providerMetadata\": {\"orgId\": \"a0819718-46f1-4df5-94e2-005712e83aaa\", \"shortName\": \"GitHub_M\", \"dateUpdated\": \"2026-08-04T19:29:14.796Z\"}}}",
      "cveMetadata": "{\"cveId\": \"CVE-2026-70477\", \"state\": \"PUBLISHED\", \"dateUpdated\": \"2026-08-05T13:51:57.817Z\", \"dateReserved\": \"2026-08-04T15:24:41.339Z\", \"assignerOrgId\": \"a0819718-46f1-4df5-94e2-005712e83aaa\", \"datePublished\": \"2026-08-04T19:29:14.796Z\", \"assignerShortName\": \"GitHub_M\"}",
      "dataType": "CVE_RECORD",
      "dataVersion": "5.2"
    }
  }
}


Log in or create an account to share your comment.




Tags
Taxonomy of the tags.




Sightings

Author Source Type Date

Nomenclature

  • Seen: The vulnerability was mentioned, discussed, or seen somewhere by the user.
  • Confirmed: The vulnerability is confirmed from an analyst perspective.
  • Published Proof of Concept: A public proof of concept is available for this vulnerability.
  • Exploited: This vulnerability was exploited and seen by the user reporting the sighting.
  • Patched: This vulnerability was successfully patched by the user reporting the sighting.
  • Not exploited: This vulnerability was not exploited or seen by the user reporting the sighting.
  • Not confirmed: The user expresses doubt about the veracity of the vulnerability.
  • Not patched: This vulnerability was not successfully patched by the user reporting the sighting.