GSD-2023-37274

Vulnerability from gsd - Updated: 2023-12-13 01:20
Details
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.
Aliases
Aliases
CVE-2023-37274
To clipboard 

{
  "GSD": {
    "alias": "CVE-2023-37274",
    "id": "GSD-2023-37274"
  },
  "gsd": {
    "metadata": {
      "exploitCode": "unknown",
      "remediation": "unknown",
      "reportConfidence": "confirmed",
      "type": "vulnerability"
    },
    "osvSchema": {
      "aliases": [
        "CVE-2023-37274"
      ],
      "details": "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": "GSD-2023-37274",
      "modified": "2023-12-13T01:20:24.882921Z",
      "schema_version": "1.4.0"
    }
  },
  "namespaces": {
    "cve.org": {
      "CVE_data_meta": {
        "ASSIGNER": "security-advisories@github.com",
        "ID": "CVE-2023-37274",
        "STATE": "PUBLIC"
      },
      "affects": {
        "vendor": {
          "vendor_data": [
            {
              "product": {
                "product_data": [
                  {
                    "product_name": "Auto-GPT",
                    "version": {
                      "version_data": [
                        {
                          "version_affected": "=",
                          "version_value": "\u003c 0.4.3"
                        }
                      ]
                    }
                  }
                ]
              },
              "vendor_name": "Significant-Gravitas"
            }
          ]
        }
      },
      "data_format": "MITRE",
      "data_type": "CVE",
      "data_version": "4.0",
      "description": {
        "description_data": [
          {
            "lang": "eng",
            "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."
          }
        ]
      },
      "impact": {
        "cvss": [
          {
            "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"
          }
        ]
      },
      "problemtype": {
        "problemtype_data": [
          {
            "description": [
              {
                "cweId": "CWE-94",
                "lang": "eng",
                "value": "CWE-94: Improper Control of Generation of Code (\u0027Code Injection\u0027)"
              }
            ]
          }
        ]
      },
      "references": {
        "reference_data": [
          {
            "name": "https://github.com/Significant-Gravitas/Auto-GPT/security/advisories/GHSA-5h38-mgp9-rj5f",
            "refsource": "MISC",
            "url": "https://github.com/Significant-Gravitas/Auto-GPT/security/advisories/GHSA-5h38-mgp9-rj5f"
          },
          {
            "name": "https://github.com/Significant-Gravitas/Auto-GPT/pull/4756",
            "refsource": "MISC",
            "url": "https://github.com/Significant-Gravitas/Auto-GPT/pull/4756"
          }
        ]
      },
      "source": {
        "advisory": "GHSA-5h38-mgp9-rj5f",
        "discovery": "UNKNOWN"
      }
    },
    "nvd.nist.gov": {
      "configurations": {
        "CVE_data_version": "4.0",
        "nodes": [
          {
            "children": [],
            "cpe_match": [
              {
                "cpe23Uri": "cpe:2.3:a:agpt:auto-gpt:*:*:*:*:*:*:*:*",
                "cpe_name": [],
                "versionEndExcluding": "0.4.3",
                "vulnerable": true
              }
            ],
            "operator": "OR"
          }
        ]
      },
      "cve": {
        "CVE_data_meta": {
          "ASSIGNER": "security-advisories@github.com",
          "ID": "CVE-2023-37274"
        },
        "data_format": "MITRE",
        "data_type": "CVE",
        "data_version": "4.0",
        "description": {
          "description_data": [
            {
              "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."
            }
          ]
        },
        "problemtype": {
          "problemtype_data": [
            {
              "description": [
                {
                  "lang": "en",
                  "value": "CWE-94"
                }
              ]
            }
          ]
        },
        "references": {
          "reference_data": [
            {
              "name": "https://github.com/Significant-Gravitas/Auto-GPT/pull/4756",
              "refsource": "MISC",
              "tags": [
                "Patch",
                "Third Party Advisory"
              ],
              "url": "https://github.com/Significant-Gravitas/Auto-GPT/pull/4756"
            },
            {
              "name": "https://github.com/Significant-Gravitas/Auto-GPT/security/advisories/GHSA-5h38-mgp9-rj5f",
              "refsource": "MISC",
              "tags": [
                "Patch",
                "Third Party Advisory"
              ],
              "url": "https://github.com/Significant-Gravitas/Auto-GPT/security/advisories/GHSA-5h38-mgp9-rj5f"
            }
          ]
        }
      },
      "impact": {
        "baseMetricV3": {
          "cvssV3": {
            "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
        }
      },
      "lastModifiedDate": "2023-07-27T14:54Z",
      "publishedDate": "2023-07-13T23:15Z"
    }
  }
}


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 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.



Detection rules are retrieved from Rulezet.