CVE-2026-62675 (GCVE-0-2026-62675)
Vulnerability from cvelistv5
Published
2026-08-21 17:49
Modified
2026-08-21 18:11
Severity ?
8.8 (High) - CVSS:3.1/AV:N/AC:L/PR:L/UI:N/S:U/C:H/I:H/A:H
CWE
  • CWE-94 - Improper Control of Generation of Code ('Code Injection')
Summary
Omnigent is an open-source AI agent framework and meta-harness for orchestrating coding agents. Prior to 0.3.0, multipart POST /v1/sessions accepts an authenticated user's agent bundle and omnigent/server/bundles.py validate_agent_bundle does not reject a tools..callable dotted Python path. omnigent/runner/tool_dispatch.py _resolve_spec_callable imports the specified module and _execute_spec_callable_tool invokes the resolved function, allowing a bundle to select subprocess.check_output and execute a local command with the runner process permissions. This can expose runner files, environment variables, credentials, workspace data, internal services, and availability without administrator access. This issue is fixed in version 0.3.0.
References
Impacted products
Vendor Product Version
omnigent-ai omnigent Version: < 0.3.0
 Create a notification for this product.
Show details on NVD website

To clipboard 

{
  "containers": {
    "adp": [
      {
        "metrics": [
          {
            "other": {
              "content": {
                "id": "CVE-2026-62675",
                "options": [
                  {
                    "Exploitation": "poc"
                  },
                  {
                    "Automatable": "no"
                  },
                  {
                    "Technical Impact": "total"
                  }
                ],
                "role": "CISA Coordinator",
                "timestamp": "2026-08-21T18:11:11.340625Z",
                "version": "2.0.3"
              },
              "type": "ssvc"
            }
          }
        ],
        "providerMetadata": {
          "dateUpdated": "2026-08-21T18:11:40.698Z",
          "orgId": "134c704f-9b21-4f2e-91b3-4a467353bcc0",
          "shortName": "CISA-ADP"
        },
        "references": [
          {
            "tags": [
              "exploit"
            ],
            "url": "https://github.com/omnigent-ai/omnigent/security/advisories/GHSA-756x-9hf6-q4h4"
          }
        ],
        "title": "CISA ADP Vulnrichment"
      }
    ],
    "cna": {
      "affected": [
        {
          "product": "omnigent",
          "vendor": "omnigent-ai",
          "versions": [
            {
              "status": "affected",
              "version": "\u003c 0.3.0"
            }
          ]
        }
      ],
      "descriptions": [
        {
          "lang": "en",
          "value": "Omnigent is an open-source AI agent framework and meta-harness for orchestrating coding agents. Prior to 0.3.0, multipart POST /v1/sessions accepts an authenticated user\u0027s agent bundle and omnigent/server/bundles.py validate_agent_bundle does not reject a tools..callable dotted Python path. omnigent/runner/tool_dispatch.py _resolve_spec_callable imports the specified module and _execute_spec_callable_tool invokes the resolved function, allowing a bundle to select subprocess.check_output and execute a local command with the runner process permissions. This can expose runner files, environment variables, credentials, workspace data, internal services, and availability without administrator access. This issue is fixed in version 0.3.0."
        }
      ],
      "metrics": [
        {
          "cvssV3_1": {
            "attackComplexity": "LOW",
            "attackVector": "NETWORK",
            "availabilityImpact": "HIGH",
            "baseScore": 8.8,
            "baseSeverity": "HIGH",
            "confidentialityImpact": "HIGH",
            "integrityImpact": "HIGH",
            "privilegesRequired": "LOW",
            "scope": "UNCHANGED",
            "userInteraction": "NONE",
            "vectorString": "CVSS:3.1/AV:N/AC:L/PR:L/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"
            }
          ]
        }
      ],
      "providerMetadata": {
        "dateUpdated": "2026-08-21T17:49:00.242Z",
        "orgId": "a0819718-46f1-4df5-94e2-005712e83aaa",
        "shortName": "GitHub_M"
      },
      "references": [
        {
          "name": "https://github.com/omnigent-ai/omnigent/security/advisories/GHSA-756x-9hf6-q4h4",
          "tags": [
            "x_refsource_CONFIRM"
          ],
          "url": "https://github.com/omnigent-ai/omnigent/security/advisories/GHSA-756x-9hf6-q4h4"
        },
        {
          "name": "https://github.com/omnigent-ai/omnigent/pull/1430",
          "tags": [
            "x_refsource_MISC"
          ],
          "url": "https://github.com/omnigent-ai/omnigent/pull/1430"
        },
        {
          "name": "https://github.com/omnigent-ai/omnigent/commit/1f3f398f41cbf97b905133c21e848621c21da6e0",
          "tags": [
            "x_refsource_MISC"
          ],
          "url": "https://github.com/omnigent-ai/omnigent/commit/1f3f398f41cbf97b905133c21e848621c21da6e0"
        },
        {
          "name": "https://github.com/omnigent-ai/omnigent/releases/tag/v0.3.0",
          "tags": [
            "x_refsource_MISC"
          ],
          "url": "https://github.com/omnigent-ai/omnigent/releases/tag/v0.3.0"
        }
      ],
      "source": {
        "advisory": "GHSA-756x-9hf6-q4h4",
        "discovery": "UNKNOWN"
      },
      "title": "Omnigent: Uploaded Agent Bundle Allows Authenticated Runner RCE via Python Callable Tools"
    }
  },
  "cveMetadata": {
    "assignerOrgId": "a0819718-46f1-4df5-94e2-005712e83aaa",
    "assignerShortName": "GitHub_M",
    "cveId": "CVE-2026-62675",
    "datePublished": "2026-08-21T17:49:00.242Z",
    "dateReserved": "2026-07-14T20:22:04.395Z",
    "dateUpdated": "2026-08-21T18:11:40.698Z",
    "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-2026-62675\", \"role\": \"CISA Coordinator\", \"options\": [{\"Exploitation\": \"poc\"}, {\"Automatable\": \"no\"}, {\"Technical Impact\": \"total\"}], \"version\": \"2.0.3\", \"timestamp\": \"2026-08-21T18:11:11.340625Z\"}}}], \"references\": [{\"url\": \"https://github.com/omnigent-ai/omnigent/security/advisories/GHSA-756x-9hf6-q4h4\", \"tags\": [\"exploit\"]}], \"providerMetadata\": {\"orgId\": \"134c704f-9b21-4f2e-91b3-4a467353bcc0\", \"shortName\": \"CISA-ADP\", \"dateUpdated\": \"2026-08-21T18:11:36.353Z\"}}], \"cna\": {\"title\": \"Omnigent: Uploaded Agent Bundle Allows Authenticated Runner RCE via Python Callable Tools\", \"source\": {\"advisory\": \"GHSA-756x-9hf6-q4h4\", \"discovery\": \"UNKNOWN\"}, \"metrics\": [{\"cvssV3_1\": {\"scope\": \"UNCHANGED\", \"version\": \"3.1\", \"baseScore\": 8.8, \"attackVector\": \"NETWORK\", \"baseSeverity\": \"HIGH\", \"vectorString\": \"CVSS:3.1/AV:N/AC:L/PR:L/UI:N/S:U/C:H/I:H/A:H\", \"integrityImpact\": \"HIGH\", \"userInteraction\": \"NONE\", \"attackComplexity\": \"LOW\", \"availabilityImpact\": \"HIGH\", \"privilegesRequired\": \"LOW\", \"confidentialityImpact\": \"HIGH\"}}], \"affected\": [{\"vendor\": \"omnigent-ai\", \"product\": \"omnigent\", \"versions\": [{\"status\": \"affected\", \"version\": \"\u003c 0.3.0\"}]}], \"references\": [{\"url\": \"https://github.com/omnigent-ai/omnigent/security/advisories/GHSA-756x-9hf6-q4h4\", \"name\": \"https://github.com/omnigent-ai/omnigent/security/advisories/GHSA-756x-9hf6-q4h4\", \"tags\": [\"x_refsource_CONFIRM\"]}, {\"url\": \"https://github.com/omnigent-ai/omnigent/pull/1430\", \"name\": \"https://github.com/omnigent-ai/omnigent/pull/1430\", \"tags\": [\"x_refsource_MISC\"]}, {\"url\": \"https://github.com/omnigent-ai/omnigent/commit/1f3f398f41cbf97b905133c21e848621c21da6e0\", \"name\": \"https://github.com/omnigent-ai/omnigent/commit/1f3f398f41cbf97b905133c21e848621c21da6e0\", \"tags\": [\"x_refsource_MISC\"]}, {\"url\": \"https://github.com/omnigent-ai/omnigent/releases/tag/v0.3.0\", \"name\": \"https://github.com/omnigent-ai/omnigent/releases/tag/v0.3.0\", \"tags\": [\"x_refsource_MISC\"]}], \"descriptions\": [{\"lang\": \"en\", \"value\": \"Omnigent is an open-source AI agent framework and meta-harness for orchestrating coding agents. Prior to 0.3.0, multipart POST /v1/sessions accepts an authenticated user\u0027s agent bundle and omnigent/server/bundles.py validate_agent_bundle does not reject a tools..callable dotted Python path. omnigent/runner/tool_dispatch.py _resolve_spec_callable imports the specified module and _execute_spec_callable_tool invokes the resolved function, allowing a bundle to select subprocess.check_output and execute a local command with the runner process permissions. This can expose runner files, environment variables, credentials, workspace data, internal services, and availability without administrator access. This issue is fixed in version 0.3.0.\"}], \"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\": \"2026-08-21T17:49:00.242Z\"}}}",
      "cveMetadata": "{\"cveId\": \"CVE-2026-62675\", \"state\": \"PUBLISHED\", \"dateUpdated\": \"2026-08-21T18:11:40.698Z\", \"dateReserved\": \"2026-07-14T20:22:04.395Z\", \"assignerOrgId\": \"a0819718-46f1-4df5-94e2-005712e83aaa\", \"datePublished\": \"2026-08-21T17:49:00.242Z\", \"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.