CVE-2023-37274 (GCVE-0-2023-37274)

Vulnerability from cvelistv5 – Published: 2023-07-13 22:33 – Updated: 2024-10-30 15:53
VLAI
Title
Python code execution sandbox escape in non-docker version in Auto-GPT
Summary
Auto-GPT is an experimental open-source application showcasing the capabilities of the GPT-4 language model. When Auto-GPT is executed directly on the host system via the provided run.sh or run.bat files, custom Python code execution is sandboxed using a temporary dedicated docker container which should not have access to any files outside of the Auto-GPT workspace directory. Before v0.4.3, the `execute_python_code` command (introduced in v0.4.1) does not sanitize the `basename` arg before writing LLM-supplied code to a file with an LLM-supplied name. This allows for a path traversal attack that can overwrite any .py file outside the workspace directory by specifying a `basename` such as `../../../main.py`. This can further be abused to achieve arbitrary code execution on the host running Auto-GPT by e.g. overwriting autogpt/main.py which will be executed outside of the docker environment meant to sandbox custom python code execution the next time Auto-GPT is started. The issue has been patched in version 0.4.3. As a workaround, the risk introduced by this vulnerability can be remediated by running Auto-GPT in a virtual machine, or another environment in which damage to files or corruption of the program is not a critical problem.
Severity
7.6 (High)
CVSS:3.1/AV:L/AC:H/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 2024-10-30 15:53 UTC
CWE
  • CWE-94 - Improper Control of Generation of Code ('Code Injection')
Assigner
References
Impacted products
Vendor Product Version CPE status
Significant-Gravitas Auto-GPT Affected: < 0.4.3
guessed Create a notification for this product.
Show details on NVD website
To clipboard 

{
  "containers": {
    "adp": [
      {
        "providerMetadata": {
          "dateUpdated": "2024-08-02T17:09:34.085Z",
          "orgId": "af854a3a-2127-422b-91ae-364da2661108",
          "shortName": "CVE"
        },
        "references": [
          {
            "name": "https://github.com/Significant-Gravitas/Auto-GPT/security/advisories/GHSA-5h38-mgp9-rj5f",
            "tags": [
              "x_refsource_CONFIRM",
              "x_transferred"
            ],
            "url": "https://github.com/Significant-Gravitas/Auto-GPT/security/advisories/GHSA-5h38-mgp9-rj5f"
          },
          {
            "name": "https://github.com/Significant-Gravitas/Auto-GPT/pull/4756",
            "tags": [
              "x_refsource_MISC",
              "x_transferred"
            ],
            "url": "https://github.com/Significant-Gravitas/Auto-GPT/pull/4756"
          }
        ],
        "title": "CVE Program Container"
      },
      {
        "metrics": [
          {
            "other": {
              "content": {
                "id": "CVE-2023-37274",
                "options": [
                  {
                    "Exploitation": "none"
                  },
                  {
                    "Automatable": "no"
                  },
                  {
                    "Technical Impact": "total"
                  }
                ],
                "role": "CISA Coordinator",
                "timestamp": "2024-10-30T15:53:50.571521Z",
                "version": "2.0.3"
              },
              "type": "ssvc"
            }
          }
        ],
        "providerMetadata": {
          "dateUpdated": "2024-10-30T15:53:58.317Z",
          "orgId": "134c704f-9b21-4f2e-91b3-4a467353bcc0",
          "shortName": "CISA-ADP"
        },
        "title": "CISA ADP Vulnrichment"
      }
    ],
    "cna": {
      "affected": [
        {
          "product": "Auto-GPT",
          "vendor": "Significant-Gravitas",
          "versions": [
            {
              "status": "affected",
              "version": "\u003c 0.4.3"
            }
          ]
        }
      ],
      "descriptions": [
        {
          "lang": "en",
          "value": "Auto-GPT is an experimental open-source application showcasing the capabilities of the GPT-4 language model. When Auto-GPT is executed directly on the host system via the provided run.sh or run.bat files, custom Python code execution is sandboxed using a temporary dedicated docker container which should not have access to any files outside of the Auto-GPT workspace directory.\nBefore v0.4.3, the `execute_python_code` command (introduced in v0.4.1) does not sanitize the `basename` arg before writing LLM-supplied code to a file with an LLM-supplied name. This allows for a path traversal attack that can overwrite any .py file outside the workspace directory by specifying a `basename` such as `../../../main.py`. This can further be abused to achieve arbitrary code execution on the host running Auto-GPT by e.g. overwriting autogpt/main.py which will be executed outside of the docker environment meant to sandbox custom python code execution the next time Auto-GPT is started. The issue has been patched in version 0.4.3. As a workaround, the risk introduced by this vulnerability can be remediated by running Auto-GPT in a virtual machine, or another environment in which damage to files or corruption of the program is not a critical problem."
        }
      ],
      "metrics": [
        {
          "cvssV3_1": {
            "attackComplexity": "HIGH",
            "attackVector": "LOCAL",
            "availabilityImpact": "HIGH",
            "baseScore": 7.6,
            "baseSeverity": "HIGH",
            "confidentialityImpact": "HIGH",
            "integrityImpact": "HIGH",
            "privilegesRequired": "LOW",
            "scope": "CHANGED",
            "userInteraction": "REQUIRED",
            "vectorString": "CVSS:3.1/AV:L/AC:H/PR:L/UI:R/S:C/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": "2023-07-13T22:33:41.290Z",
        "orgId": "a0819718-46f1-4df5-94e2-005712e83aaa",
        "shortName": "GitHub_M"
      },
      "references": [
        {
          "name": "https://github.com/Significant-Gravitas/Auto-GPT/security/advisories/GHSA-5h38-mgp9-rj5f",
          "tags": [
            "x_refsource_CONFIRM"
          ],
          "url": "https://github.com/Significant-Gravitas/Auto-GPT/security/advisories/GHSA-5h38-mgp9-rj5f"
        },
        {
          "name": "https://github.com/Significant-Gravitas/Auto-GPT/pull/4756",
          "tags": [
            "x_refsource_MISC"
          ],
          "url": "https://github.com/Significant-Gravitas/Auto-GPT/pull/4756"
        }
      ],
      "source": {
        "advisory": "GHSA-5h38-mgp9-rj5f",
        "discovery": "UNKNOWN"
      },
      "title": "Python code execution sandbox escape in non-docker version in Auto-GPT"
    }
  },
  "cveMetadata": {
    "assignerOrgId": "a0819718-46f1-4df5-94e2-005712e83aaa",
    "assignerShortName": "GitHub_M",
    "cveId": "CVE-2023-37274",
    "datePublished": "2023-07-13T22:33:41.290Z",
    "dateReserved": "2023-06-29T19:35:26.440Z",
    "dateUpdated": "2024-10-30T15:53:58.317Z",
    "state": "PUBLISHED"
  },
  "dataType": "CVE_RECORD",
  "dataVersion": "5.1",
  "vulnerability-lookup:meta": {
    "epss": {
      "cve": "CVE-2023-37274",
      "date": "2026-10-07",
      "epss": "0.00352",
      "percentile": "0.26743"
    },
    "fkie_nvd": {
      "configurations": [
        {
          "nodes": [
            {
              "cpeMatch": [
                {
                  "criteria": "cpe:2.3:a:agpt:auto-gpt:*:*:*:*:*:*:*:*",
                  "matchCriteriaId": "10E8D9E9-E73C-4B20-989E-1D432F7ED3BB",
                  "versionEndExcluding": "0.4.3",
                  "vulnerable": true
                }
              ],
              "negate": false,
              "operator": "OR"
            }
          ]
        }
      ],
      "descriptions": [
        {
          "lang": "en",
          "value": "Auto-GPT is an experimental open-source application showcasing the capabilities of the GPT-4 language model. When Auto-GPT is executed directly on the host system via the provided run.sh or run.bat files, custom Python code execution is sandboxed using a temporary dedicated docker container which should not have access to any files outside of the Auto-GPT workspace directory.\nBefore v0.4.3, the `execute_python_code` command (introduced in v0.4.1) does not sanitize the `basename` arg before writing LLM-supplied code to a file with an LLM-supplied name. This allows for a path traversal attack that can overwrite any .py file outside the workspace directory by specifying a `basename` such as `../../../main.py`. This can further be abused to achieve arbitrary code execution on the host running Auto-GPT by e.g. overwriting autogpt/main.py which will be executed outside of the docker environment meant to sandbox custom python code execution the next time Auto-GPT is started. The issue has been patched in version 0.4.3. As a workaround, the risk introduced by this vulnerability can be remediated by running Auto-GPT in a virtual machine, or another environment in which damage to files or corruption of the program is not a critical problem."
        }
      ],
      "id": "CVE-2023-37274",
      "lastModified": "2024-11-21T08:11:22.300",
      "metrics": {
        "cvssMetricV31": [
          {
            "cvssData": {
              "attackComplexity": "HIGH",
              "attackVector": "LOCAL",
              "availabilityImpact": "HIGH",
              "baseScore": 7.5,
              "baseSeverity": "HIGH",
              "confidentialityImpact": "HIGH",
              "integrityImpact": "HIGH",
              "privilegesRequired": "LOW",
              "scope": "CHANGED",
              "userInteraction": "REQUIRED",
              "vectorString": "CVSS:3.1/AV:L/AC:H/PR:L/UI:R/S:C/C:H/I:H/A:H",
              "version": "3.1"
            },
            "exploitabilityScore": 0.8,
            "impactScore": 6.0,
            "source": "security-advisories@github.com",
            "type": "Secondary"
          },
          {
            "cvssData": {
              "attackComplexity": "LOW",
              "attackVector": "LOCAL",
              "availabilityImpact": "HIGH",
              "baseScore": 7.8,
              "baseSeverity": "HIGH",
              "confidentialityImpact": "HIGH",
              "integrityImpact": "HIGH",
              "privilegesRequired": "LOW",
              "scope": "UNCHANGED",
              "userInteraction": "NONE",
              "vectorString": "CVSS:3.1/AV:L/AC:L/PR:L/UI:N/S:U/C:H/I:H/A:H",
              "version": "3.1"
            },
            "exploitabilityScore": 1.8,
            "impactScore": 5.9,
            "source": "nvd@nist.gov",
            "type": "Primary"
          }
        ]
      },
      "published": "2023-07-13T23:15:10.820",
      "references": [
        {
          "source": "security-advisories@github.com",
          "tags": [
            "Patch",
            "Third Party Advisory"
          ],
          "url": "https://github.com/Significant-Gravitas/Auto-GPT/pull/4756"
        },
        {
          "source": "security-advisories@github.com",
          "tags": [
            "Patch",
            "Third Party Advisory"
          ],
          "url": "https://github.com/Significant-Gravitas/Auto-GPT/security/advisories/GHSA-5h38-mgp9-rj5f"
        },
        {
          "source": "af854a3a-2127-422b-91ae-364da2661108",
          "tags": [
            "Patch",
            "Third Party Advisory"
          ],
          "url": "https://github.com/Significant-Gravitas/Auto-GPT/pull/4756"
        },
        {
          "source": "af854a3a-2127-422b-91ae-364da2661108",
          "tags": [
            "Patch",
            "Third Party Advisory"
          ],
          "url": "https://github.com/Significant-Gravitas/Auto-GPT/security/advisories/GHSA-5h38-mgp9-rj5f"
        }
      ],
      "sourceIdentifier": "security-advisories@github.com",
      "vulnStatus": "Modified",
      "weaknesses": [
        {
          "description": [
            {
              "lang": "en",
              "value": "CWE-94"
            }
          ],
          "source": "security-advisories@github.com",
          "type": "Primary"
        }
      ]
    },
    "nvd": {
      "cve": {
        "affected": [
          {
            "affectedData": [
              {
                "product": "Auto-GPT",
                "vendor": "Significant-Gravitas",
                "versions": [
                  {
                    "status": "affected",
                    "version": "\u003c 0.4.3"
                  }
                ]
              }
            ],
            "source": "security-advisories@github.com"
          }
        ],
        "configurations": [
          {
            "nodes": [
              {
                "cpeMatch": [
                  {
                    "criteria": "cpe:2.3:a:agpt:autogpt_classic:*:*:*:*:*:*:*:*",
                    "matchCriteriaId": "1FD0FE0D-77C7-4657-888B-B043D42D047D",
                    "versionEndExcluding": "0.4.3",
                    "vulnerable": true
                  }
                ],
                "negate": false,
                "operator": "OR"
              }
            ]
          }
        ],
        "cveTags": [],
        "descriptions": [
          {
            "lang": "en",
            "value": "Auto-GPT is an experimental open-source application showcasing the capabilities of the GPT-4 language model. When Auto-GPT is executed directly on the host system via the provided run.sh or run.bat files, custom Python code execution is sandboxed using a temporary dedicated docker container which should not have access to any files outside of the Auto-GPT workspace directory.\nBefore v0.4.3, the `execute_python_code` command (introduced in v0.4.1) does not sanitize the `basename` arg before writing LLM-supplied code to a file with an LLM-supplied name. This allows for a path traversal attack that can overwrite any .py file outside the workspace directory by specifying a `basename` such as `../../../main.py`. This can further be abused to achieve arbitrary code execution on the host running Auto-GPT by e.g. overwriting autogpt/main.py which will be executed outside of the docker environment meant to sandbox custom python code execution the next time Auto-GPT is started. The issue has been patched in version 0.4.3. As a workaround, the risk introduced by this vulnerability can be remediated by running Auto-GPT in a virtual machine, or another environment in which damage to files or corruption of the program is not a critical problem."
          }
        ],
        "id": "CVE-2023-37274",
        "lastModified": "2026-06-17T06:07:51.993",
        "metrics": {
          "cvssMetricV31": [
            {
              "cvssData": {
                "attackComplexity": "HIGH",
                "attackVector": "LOCAL",
                "availabilityImpact": "HIGH",
                "baseScore": 7.5,
                "baseSeverity": "HIGH",
                "confidentialityImpact": "HIGH",
                "integrityImpact": "HIGH",
                "privilegesRequired": "LOW",
                "scope": "CHANGED",
                "userInteraction": "REQUIRED",
                "vectorString": "CVSS:3.1/AV:L/AC:H/PR:L/UI:R/S:C/C:H/I:H/A:H",
                "version": "3.1"
              },
              "exploitabilityScore": 0.8,
              "impactScore": 6.0,
              "source": "security-advisories@github.com",
              "type": "Secondary"
            },
            {
              "cvssData": {
                "attackComplexity": "LOW",
                "attackVector": "LOCAL",
                "availabilityImpact": "HIGH",
                "baseScore": 7.8,
                "baseSeverity": "HIGH",
                "confidentialityImpact": "HIGH",
                "integrityImpact": "HIGH",
                "privilegesRequired": "LOW",
                "scope": "UNCHANGED",
                "userInteraction": "NONE",
                "vectorString": "CVSS:3.1/AV:L/AC:L/PR:L/UI:N/S:U/C:H/I:H/A:H",
                "version": "3.1"
              },
              "exploitabilityScore": 1.8,
              "impactScore": 5.9,
              "source": "nvd@nist.gov",
              "type": "Primary"
            }
          ],
          "ssvcV203": [
            {
              "source": "134c704f-9b21-4f2e-91b3-4a467353bcc0",
              "ssvcData": {
                "id": "CVE-2023-37274",
                "options": [
                  {
                    "exploitation": "none"
                  },
                  {
                    "automatable": "no"
                  },
                  {
                    "technicalImpact": "total"
                  }
                ],
                "role": "CISA Coordinator",
                "timestamp": "2024-10-30T15:53:50.571521Z",
                "version": "2.0.3"
              }
            }
          ]
        },
        "published": "2023-07-13T23:15:10.820",
        "references": [
          {
            "source": "security-advisories@github.com",
            "tags": [
              "Patch",
              "Third Party Advisory"
            ],
            "url": "https://github.com/Significant-Gravitas/Auto-GPT/pull/4756"
          },
          {
            "source": "security-advisories@github.com",
            "tags": [
              "Patch",
              "Third Party Advisory"
            ],
            "url": "https://github.com/Significant-Gravitas/Auto-GPT/security/advisories/GHSA-5h38-mgp9-rj5f"
          },
          {
            "source": "af854a3a-2127-422b-91ae-364da2661108",
            "tags": [
              "Patch",
              "Third Party Advisory"
            ],
            "url": "https://github.com/Significant-Gravitas/Auto-GPT/pull/4756"
          },
          {
            "source": "af854a3a-2127-422b-91ae-364da2661108",
            "tags": [
              "Patch",
              "Third Party Advisory"
            ],
            "url": "https://github.com/Significant-Gravitas/Auto-GPT/security/advisories/GHSA-5h38-mgp9-rj5f"
          }
        ],
        "sourceIdentifier": "security-advisories@github.com",
        "vulnStatus": "Analyzed",
        "weaknesses": [
          {
            "description": [
              {
                "lang": "en",
                "value": "CWE-94"
              }
            ],
            "source": "security-advisories@github.com",
            "type": "Secondary"
          }
        ]
      }
    },
    "redhat_vex": {
      "current_release_date": "2025-05-28T23:44:28+00:00",
      "cve": "CVE-2023-37274",
      "id": "CVE-2023-37274",
      "initial_release_date": "2023-01-01T00:00:00+00:00",
      "product_status:known_not_affected": "1",
      "source": "Red Hat CSAF VEX",
      "status": "final",
      "title": "Python code execution sandbox escape in non-docker version in Auto-GPT",
      "url": "https://security.access.redhat.com/data/csaf/v2/vex/2023/cve-2023-37274.json",
      "version": "3"
    },
    "vulnrichment": {
      "containers": {
        "adp": [
          {
            "providerMetadata": {
              "dateUpdated": "2024-08-02T17:09:34.085Z",
              "orgId": "af854a3a-2127-422b-91ae-364da2661108",
              "shortName": "CVE"
            },
            "references": [
              {
                "name": "https://github.com/Significant-Gravitas/Auto-GPT/security/advisories/GHSA-5h38-mgp9-rj5f",
                "tags": [
                  "x_refsource_CONFIRM",
                  "x_transferred"
                ],
                "url": "https://github.com/Significant-Gravitas/Auto-GPT/security/advisories/GHSA-5h38-mgp9-rj5f"
              },
              {
                "name": "https://github.com/Significant-Gravitas/Auto-GPT/pull/4756",
                "tags": [
                  "x_refsource_MISC",
                  "x_transferred"
                ],
                "url": "https://github.com/Significant-Gravitas/Auto-GPT/pull/4756"
              }
            ],
            "title": "CVE Program Container"
          },
          {
            "metrics": [
              {
                "other": {
                  "content": {
                    "id": "CVE-2023-37274",
                    "options": [
                      {
                        "Exploitation": "none"
                      },
                      {
                        "Automatable": "no"
                      },
                      {
                        "Technical Impact": "total"
                      }
                    ],
                    "role": "CISA Coordinator",
                    "timestamp": "2024-10-30T15:53:50.571521Z",
                    "version": "2.0.3"
                  },
                  "type": "ssvc"
                }
              }
            ],
            "providerMetadata": {
              "dateUpdated": "2024-10-30T15:53:54.470Z",
              "orgId": "134c704f-9b21-4f2e-91b3-4a467353bcc0",
              "shortName": "CISA-ADP"
            },
            "title": "CISA ADP Vulnrichment"
          }
        ],
        "cna": {
          "affected": [
            {
              "product": "Auto-GPT",
              "vendor": "Significant-Gravitas",
              "versions": [
                {
                  "status": "affected",
                  "version": "\u003c 0.4.3"
                }
              ]
            }
          ],
          "descriptions": [
            {
              "lang": "en",
              "value": "Auto-GPT is an experimental open-source application showcasing the capabilities of the GPT-4 language model. When Auto-GPT is executed directly on the host system via the provided run.sh or run.bat files, custom Python code execution is sandboxed using a temporary dedicated docker container which should not have access to any files outside of the Auto-GPT workspace directory.\nBefore v0.4.3, the `execute_python_code` command (introduced in v0.4.1) does not sanitize the `basename` arg before writing LLM-supplied code to a file with an LLM-supplied name. This allows for a path traversal attack that can overwrite any .py file outside the workspace directory by specifying a `basename` such as `../../../main.py`. This can further be abused to achieve arbitrary code execution on the host running Auto-GPT by e.g. overwriting autogpt/main.py which will be executed outside of the docker environment meant to sandbox custom python code execution the next time Auto-GPT is started. The issue has been patched in version 0.4.3. As a workaround, the risk introduced by this vulnerability can be remediated by running Auto-GPT in a virtual machine, or another environment in which damage to files or corruption of the program is not a critical problem."
            }
          ],
          "metrics": [
            {
              "cvssV3_1": {
                "attackComplexity": "HIGH",
                "attackVector": "LOCAL",
                "availabilityImpact": "HIGH",
                "baseScore": 7.6,
                "baseSeverity": "HIGH",
                "confidentialityImpact": "HIGH",
                "integrityImpact": "HIGH",
                "privilegesRequired": "LOW",
                "scope": "CHANGED",
                "userInteraction": "REQUIRED",
                "vectorString": "CVSS:3.1/AV:L/AC:H/PR:L/UI:R/S:C/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": "2023-07-13T22:33:41.290Z",
            "orgId": "a0819718-46f1-4df5-94e2-005712e83aaa",
            "shortName": "GitHub_M"
          },
          "references": [
            {
              "name": "https://github.com/Significant-Gravitas/Auto-GPT/security/advisories/GHSA-5h38-mgp9-rj5f",
              "tags": [
                "x_refsource_CONFIRM"
              ],
              "url": "https://github.com/Significant-Gravitas/Auto-GPT/security/advisories/GHSA-5h38-mgp9-rj5f"
            },
            {
              "name": "https://github.com/Significant-Gravitas/Auto-GPT/pull/4756",
              "tags": [
                "x_refsource_MISC"
              ],
              "url": "https://github.com/Significant-Gravitas/Auto-GPT/pull/4756"
            }
          ],
          "source": {
            "advisory": "GHSA-5h38-mgp9-rj5f",
            "discovery": "UNKNOWN"
          },
          "title": "Python code execution sandbox escape in non-docker version in Auto-GPT"
        }
      },
      "cveMetadata": {
        "assignerOrgId": "a0819718-46f1-4df5-94e2-005712e83aaa",
        "assignerShortName": "GitHub_M",
        "cveId": "CVE-2023-37274",
        "datePublished": "2023-07-13T22:33:41.290Z",
        "dateReserved": "2023-06-29T19:35:26.440Z",
        "dateUpdated": "2024-10-30T15:53:58.317Z",
        "state": "PUBLISHED"
      },
      "dataType": "CVE_RECORD",
      "dataVersion": "5.1"
    }
  }
}



Log in or create an account to share your comment.




Tags
Taxonomy of the tags.





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.



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.