CVE-2026-62676 (GCVE-0-2026-62676)

Vulnerability from cvelistv5 – Published: 2026-08-21 17:42 – Updated: 2026-08-26 17:32
VLAI
Title
Omnigent Guardrail policy bypass: shell-command parser fails open in policies/builtins/_shell.py
Summary
Omnigent is an open-source AI agent framework and meta-harness for orchestrating coding agents. Prior to 0.3.0, the shared shell-command parser in omnigent/policies/builtins/_shell.py fails to recognize combined interpreter flags, the timeout, nice, setsid, and stdbuf wrappers, command substitutions, and a single background control operator. A gated git push or gh write hidden with these forms produces no parsed operation, causing the github.py write_repos and write_branches allowlist and the working_dir.py workspace confinement policies to abstain and allow the command. An authenticated or prompt-injected agent can therefore push to an unauthorized repository or branch or escape the intended workspace. This issue is fixed in version 0.3.0.
Severity
7.1 (High)
CVSS:3.1/AV:N/AC:L/PR:L/UI:N/S:U/C:H/I:L/A:N
SSVC
Exploitation: none Automatable: no Technical Impact: partial
CISA Coordinator · CISA-ADP (v2.0.3)
Decision recorded 2026-08-26 17:31 UTC
CWE
  • CWE-184 - Incomplete List of Disallowed Inputs
Assigner
GitHub_M CNA under the mitre root
CNA scorecard C 72/100 over 7771 records in the last 180 days details
References
Impacted products
Vendor Product Version CPE status
omnigent-ai omnigent Affected: < 0.3.0
guessed Create a notification for this product.
Show details on NVD website
To clipboard 

{
  "containers": {
    "adp": [
      {
        "metrics": [
          {
            "other": {
              "content": {
                "id": "CVE-2026-62676",
                "options": [
                  {
                    "Exploitation": "none"
                  },
                  {
                    "Automatable": "no"
                  },
                  {
                    "Technical Impact": "partial"
                  }
                ],
                "role": "CISA Coordinator",
                "timestamp": "2026-08-26T17:31:50.102854Z",
                "version": "2.0.3"
              },
              "type": "ssvc"
            }
          }
        ],
        "providerMetadata": {
          "dateUpdated": "2026-08-26T17:32:00.761Z",
          "orgId": "134c704f-9b21-4f2e-91b3-4a467353bcc0",
          "shortName": "CISA-ADP"
        },
        "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, the shared shell-command parser in omnigent/policies/builtins/_shell.py fails to recognize combined interpreter flags, the timeout, nice, setsid, and stdbuf wrappers, command substitutions, and a single background control operator. A gated git push or gh write hidden with these forms produces no parsed operation, causing the github.py write_repos and write_branches allowlist and the working_dir.py workspace confinement policies to abstain and allow the command. An authenticated or prompt-injected agent can therefore push to an unauthorized repository or branch or escape the intended workspace. This issue is fixed in version 0.3.0."
        }
      ],
      "metrics": [
        {
          "cvssV3_1": {
            "attackComplexity": "LOW",
            "attackVector": "NETWORK",
            "availabilityImpact": "NONE",
            "baseScore": 7.1,
            "baseSeverity": "HIGH",
            "confidentialityImpact": "HIGH",
            "integrityImpact": "LOW",
            "privilegesRequired": "LOW",
            "scope": "UNCHANGED",
            "userInteraction": "NONE",
            "vectorString": "CVSS:3.1/AV:N/AC:L/PR:L/UI:N/S:U/C:H/I:L/A:N",
            "version": "3.1"
          }
        }
      ],
      "problemTypes": [
        {
          "descriptions": [
            {
              "cweId": "CWE-184",
              "description": "CWE-184: Incomplete List of Disallowed Inputs",
              "lang": "en",
              "type": "CWE"
            }
          ]
        }
      ],
      "providerMetadata": {
        "dateUpdated": "2026-08-21T17:42:21.563Z",
        "orgId": "a0819718-46f1-4df5-94e2-005712e83aaa",
        "shortName": "GitHub_M"
      },
      "references": [
        {
          "name": "https://github.com/omnigent-ai/omnigent/security/advisories/GHSA-7mqg-cx4g-x2rf",
          "tags": [
            "x_refsource_CONFIRM"
          ],
          "url": "https://github.com/omnigent-ai/omnigent/security/advisories/GHSA-7mqg-cx4g-x2rf"
        },
        {
          "name": "https://github.com/omnigent-ai/omnigent/pull/389",
          "tags": [
            "x_refsource_MISC"
          ],
          "url": "https://github.com/omnigent-ai/omnigent/pull/389"
        },
        {
          "name": "https://github.com/omnigent-ai/omnigent/commit/1a05b7b139ef504bf2be89bf37918abe104fb95c",
          "tags": [
            "x_refsource_MISC"
          ],
          "url": "https://github.com/omnigent-ai/omnigent/commit/1a05b7b139ef504bf2be89bf37918abe104fb95c"
        },
        {
          "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-7mqg-cx4g-x2rf",
        "discovery": "UNKNOWN"
      },
      "title": "Omnigent Guardrail policy bypass: shell-command parser fails open in policies/builtins/_shell.py"
    }
  },
  "cveMetadata": {
    "assignerOrgId": "a0819718-46f1-4df5-94e2-005712e83aaa",
    "assignerShortName": "GitHub_M",
    "cveId": "CVE-2026-62676",
    "datePublished": "2026-08-21T17:42:21.563Z",
    "dateReserved": "2026-07-14T20:22:04.395Z",
    "dateUpdated": "2026-08-26T17:32:00.761Z",
    "state": "PUBLISHED"
  },
  "dataType": "CVE_RECORD",
  "dataVersion": "5.2",
  "vulnerability-lookup:meta": {
    "epss": {
      "cve": "CVE-2026-62676",
      "date": "2026-10-16",
      "epss": "0.00402",
      "percentile": "0.32905"
    },
    "nvd": {
      "cve": {
        "affected": [
          {
            "affectedData": [
              {
                "product": "omnigent",
                "vendor": "omnigent-ai",
                "versions": [
                  {
                    "status": "affected",
                    "version": "\u003c 0.3.0"
                  }
                ]
              }
            ],
            "source": "security-advisories@github.com"
          }
        ],
        "cveTags": [],
        "descriptions": [
          {
            "lang": "en",
            "value": "Omnigent is an open-source AI agent framework and meta-harness for orchestrating coding agents. Prior to 0.3.0, the shared shell-command parser in omnigent/policies/builtins/_shell.py fails to recognize combined interpreter flags, the timeout, nice, setsid, and stdbuf wrappers, command substitutions, and a single background control operator. A gated git push or gh write hidden with these forms produces no parsed operation, causing the github.py write_repos and write_branches allowlist and the working_dir.py workspace confinement policies to abstain and allow the command. An authenticated or prompt-injected agent can therefore push to an unauthorized repository or branch or escape the intended workspace. This issue is fixed in version 0.3.0."
          },
          {
            "lang": "es",
            "value": "Omnigent es un framework de agente de IA de c\u00f3digo abierto y meta-arn\u00e9s para orquestar agentes de codificaci\u00f3n. Antes de la versi\u00f3n 0.3.0, el analizador de comandos de shell compartido en omnigent/policies/builtins/_shell.py falla al reconocer indicadores de int\u00e9rprete combinados, los envoltorios timeout, nice, setsid y stdbuf, sustituciones de comandos y un \u00fanico operador de control en segundo plano. Un git push o gh write restringido oculto con estas formas no produce ninguna operaci\u00f3n analizada, lo que hace que la lista de permitidos write_repos y write_branches de github.py y las pol\u00edticas de confinamiento del espacio de trabajo de working_dir.py se abstengan y permitan el comando. Un agente autenticado o inyectado por prompt puede, por lo tanto, hacer push a un repositorio o rama no autorizados o escapar del espacio de trabajo previsto. Este problema se ha corregido en la versi\u00f3n 0.3.0."
          }
        ],
        "id": "CVE-2026-62676",
        "lastModified": "2026-10-14T21:10:00.183",
        "metrics": {
          "cvssMetricV31": [
            {
              "cvssData": {
                "attackComplexity": "LOW",
                "attackVector": "NETWORK",
                "availabilityImpact": "NONE",
                "baseScore": 7.1,
                "baseSeverity": "HIGH",
                "confidentialityImpact": "HIGH",
                "integrityImpact": "LOW",
                "privilegesRequired": "LOW",
                "scope": "UNCHANGED",
                "userInteraction": "NONE",
                "vectorString": "CVSS:3.1/AV:N/AC:L/PR:L/UI:N/S:U/C:H/I:L/A:N",
                "version": "3.1"
              },
              "exploitabilityScore": 2.8,
              "impactScore": 4.2,
              "source": "security-advisories@github.com",
              "type": "Secondary"
            }
          ],
          "ssvcV203": [
            {
              "source": "134c704f-9b21-4f2e-91b3-4a467353bcc0",
              "ssvcData": {
                "id": "CVE-2026-62676",
                "options": [
                  {
                    "exploitation": "none"
                  },
                  {
                    "automatable": "no"
                  },
                  {
                    "technicalImpact": "partial"
                  }
                ],
                "role": "CISA Coordinator",
                "timestamp": "2026-08-26T17:31:50.102854Z",
                "version": "2.0.3"
              }
            }
          ]
        },
        "published": "2026-08-21T18:16:49.743",
        "references": [
          {
            "source": "security-advisories@github.com",
            "url": "https://github.com/omnigent-ai/omnigent/commit/1a05b7b139ef504bf2be89bf37918abe104fb95c"
          },
          {
            "source": "security-advisories@github.com",
            "url": "https://github.com/omnigent-ai/omnigent/pull/389"
          },
          {
            "source": "security-advisories@github.com",
            "url": "https://github.com/omnigent-ai/omnigent/releases/tag/v0.3.0"
          },
          {
            "source": "security-advisories@github.com",
            "url": "https://github.com/omnigent-ai/omnigent/security/advisories/GHSA-7mqg-cx4g-x2rf"
          }
        ],
        "sourceIdentifier": "security-advisories@github.com",
        "vulnStatus": "Deferred",
        "weaknesses": [
          {
            "description": [
              {
                "lang": "en",
                "value": "CWE-184"
              }
            ],
            "source": "security-advisories@github.com",
            "type": "Secondary"
          }
        ]
      }
    },
    "vulnrichment": {
      "containers": {
        "adp": [
          {
            "metrics": [
              {
                "other": {
                  "content": {
                    "id": "CVE-2026-62676",
                    "options": [
                      {
                        "Exploitation": "none"
                      },
                      {
                        "Automatable": "no"
                      },
                      {
                        "Technical Impact": "partial"
                      }
                    ],
                    "role": "CISA Coordinator",
                    "timestamp": "2026-08-26T17:31:50.102854Z",
                    "version": "2.0.3"
                  },
                  "type": "ssvc"
                }
              }
            ],
            "providerMetadata": {
              "dateUpdated": "2026-08-26T17:31:56.422Z",
              "orgId": "134c704f-9b21-4f2e-91b3-4a467353bcc0",
              "shortName": "CISA-ADP"
            },
            "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, the shared shell-command parser in omnigent/policies/builtins/_shell.py fails to recognize combined interpreter flags, the timeout, nice, setsid, and stdbuf wrappers, command substitutions, and a single background control operator. A gated git push or gh write hidden with these forms produces no parsed operation, causing the github.py write_repos and write_branches allowlist and the working_dir.py workspace confinement policies to abstain and allow the command. An authenticated or prompt-injected agent can therefore push to an unauthorized repository or branch or escape the intended workspace. This issue is fixed in version 0.3.0."
            }
          ],
          "metrics": [
            {
              "cvssV3_1": {
                "attackComplexity": "LOW",
                "attackVector": "NETWORK",
                "availabilityImpact": "NONE",
                "baseScore": 7.1,
                "baseSeverity": "HIGH",
                "confidentialityImpact": "HIGH",
                "integrityImpact": "LOW",
                "privilegesRequired": "LOW",
                "scope": "UNCHANGED",
                "userInteraction": "NONE",
                "vectorString": "CVSS:3.1/AV:N/AC:L/PR:L/UI:N/S:U/C:H/I:L/A:N",
                "version": "3.1"
              }
            }
          ],
          "problemTypes": [
            {
              "descriptions": [
                {
                  "cweId": "CWE-184",
                  "description": "CWE-184: Incomplete List of Disallowed Inputs",
                  "lang": "en",
                  "type": "CWE"
                }
              ]
            }
          ],
          "providerMetadata": {
            "dateUpdated": "2026-08-21T17:42:21.563Z",
            "orgId": "a0819718-46f1-4df5-94e2-005712e83aaa",
            "shortName": "GitHub_M"
          },
          "references": [
            {
              "name": "https://github.com/omnigent-ai/omnigent/security/advisories/GHSA-7mqg-cx4g-x2rf",
              "tags": [
                "x_refsource_CONFIRM"
              ],
              "url": "https://github.com/omnigent-ai/omnigent/security/advisories/GHSA-7mqg-cx4g-x2rf"
            },
            {
              "name": "https://github.com/omnigent-ai/omnigent/pull/389",
              "tags": [
                "x_refsource_MISC"
              ],
              "url": "https://github.com/omnigent-ai/omnigent/pull/389"
            },
            {
              "name": "https://github.com/omnigent-ai/omnigent/commit/1a05b7b139ef504bf2be89bf37918abe104fb95c",
              "tags": [
                "x_refsource_MISC"
              ],
              "url": "https://github.com/omnigent-ai/omnigent/commit/1a05b7b139ef504bf2be89bf37918abe104fb95c"
            },
            {
              "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-7mqg-cx4g-x2rf",
            "discovery": "UNKNOWN"
          },
          "title": "Omnigent Guardrail policy bypass: shell-command parser fails open in policies/builtins/_shell.py"
        }
      },
      "cveMetadata": {
        "assignerOrgId": "a0819718-46f1-4df5-94e2-005712e83aaa",
        "assignerShortName": "GitHub_M",
        "cveId": "CVE-2026-62676",
        "datePublished": "2026-08-21T17:42:21.563Z",
        "dateReserved": "2026-07-14T20:22:04.395Z",
        "dateUpdated": "2026-08-26T17:32:00.761Z",
        "state": "PUBLISHED"
      },
      "dataType": "CVE_RECORD",
      "dataVersion": "5.2"
    }
  }
}



Log in or create an account to share your comment.




Tags
Taxonomy of the tags.




Drag nodes to arrange them. Double-click a related vulnerability to open it, or a source to visit its link. The Physics button on the left tunes the layout and the simulation; the legend at the bottom left hides or shows nodes by kind and by sighting type.

Forecast uses a logistic model when the trend is rising, or an exponential decay model when the trend is falling. Fitted via linearized least squares.

Sightings

Author Source Type Date Other

Nomenclature

  • Seen: The vulnerability was mentioned, discussed, or observed by the user.
  • Confirmed: The vulnerability has been validated from an analyst's perspective.
  • Published Proof of Concept: A public proof of concept is available for this vulnerability.
  • Exploited: The vulnerability was observed as exploited by the user who reported the sighting.
  • Patched: The vulnerability was observed as successfully patched by the user who reported the sighting.
  • Not exploited: The vulnerability was not observed as exploited by the user who reported the sighting.
  • Not confirmed: The user expressed doubt about the validity of the vulnerability.
  • Not patched: The vulnerability was not observed as successfully patched by the user who reported the sighting.
Vulnerability timeline

Sightings and recorded dates, grouped by day · UTC

JSON

Loading timeline…




    Related by attack behaviour

    Vulnerabilities whose description is nearest to this one in the vector space of the CIRCL/vulnerability-attack-technique-biencoder model. This is a similarity search over the bi-encoder space (plain cosine), not a classification, and it has no measured accuracy.