CVE-2023-37273

Auto-GPT is an experimental open-source application showcasing the capabilities of the GPT-4 language model. Running Auto-GPT version prior to 0.4.3 by cloning the git repo and executing `docker compose run auto-gpt` in the repo root uses a different docker-compose.yml file from the one suggested in the official docker set up instructions. The docker-compose.yml file located in the repo root mounts itself into the docker container without write protection. This means that if malicious custom python code is executed via the `execute_python_file` and `execute_python_code` commands, it can overwrite the docker-compose.yml file and abuse it to gain control of the host system the next time Auto-GPT is started. The issue has been patched in version 0.4.3.

CVSS v3 8.1 HIGH

8.1^/10

CVSS v3 : HIGH

Vector :

Exploitability : 1.5 / Impact : 6.0

Attack Vector LOCAL

Attack Complexity LOW

Privileges Required LOW

User Interaction REQUIRED

Confidentiality Impact HIGH

Integrity Impact HIGH

Availability Impact LOW

Scope CHANGED

References

Link	Resource
https://github.com/Significant-Gravitas/Auto-GPT/pull/4761	Patch Third Party Advisory
https://github.com/Significant-Gravitas/Auto-GPT/security/advisories/GHSA-x5gj-2chr-4ch6	Patch Third Party Advisory
https://github.com/Significant-Gravitas/Auto-GPT/pull/4761	Patch Third Party Advisory
https://github.com/Significant-Gravitas/Auto-GPT/security/advisories/GHSA-x5gj-2chr-4ch6	Patch Third Party Advisory

Configurations

Configuration 1 (hide)

cpe:2.3:a:agpt:auto-gpt:*:*:*:*:*:*:*:*

History

No history.

Information

Published : 2023-07-13 23:15

Updated : 2024-11-21 08:11

NVD link : CVE-2023-37273

Mitre link : CVE-2023-37273

CVE.ORG link : CVE-2023-37273

JSON object : View

Products Affected

agpt

auto-gpt

CWE

CWE-94

Improper Control of Generation of Code ('Code Injection')

{"id": "CVE-2023-37273", "cveTags": [], "metrics": {"cvssMetricV31": [{"type": "Secondary", "source": "security-advisories@github.com", "cvssData": {"scope": "CHANGED", "version": "3.1", "baseScore": 8.1, "attackVector": "LOCAL", "baseSeverity": "HIGH", "vectorString": "CVSS:3.1/AV:L/AC:L/PR:L/UI:R/S:C/C:H/I:H/A:L", "integrityImpact": "HIGH", "userInteraction": "REQUIRED", "attackComplexity": "LOW", "availabilityImpact": "LOW", "privilegesRequired": "LOW", "confidentialityImpact": "HIGH"}, "impactScore": 6.0, "exploitabilityScore": 1.5}, {"type": "Primary", "source": "nvd@nist.gov", "cvssData": {"scope": "CHANGED", "version": "3.1", "baseScore": 8.8, "attackVector": "LOCAL", "baseSeverity": "HIGH", "vectorString": "CVSS:3.1/AV:L/AC:L/PR:L/UI:N/S:C/C:H/I:H/A:H", "integrityImpact": "HIGH", "userInteraction": "NONE", "attackComplexity": "LOW", "availabilityImpact": "HIGH", "privilegesRequired": "LOW", "confidentialityImpact": "HIGH"}, "impactScore": 6.0, "exploitabilityScore": 2.0}]}, "published": "2023-07-13T23:15:10.747", "references": [{"url": "https://github.com/Significant-Gravitas/Auto-GPT/pull/4761", "tags": ["Patch", "Third Party Advisory"], "source": "security-advisories@github.com"}, {"url": "https://github.com/Significant-Gravitas/Auto-GPT/security/advisories/GHSA-x5gj-2chr-4ch6", "tags": ["Patch", "Third Party Advisory"], "source": "security-advisories@github.com"}, {"url": "https://github.com/Significant-Gravitas/Auto-GPT/pull/4761", "tags": ["Patch", "Third Party Advisory"], "source": "af854a3a-2127-422b-91ae-364da2661108"}, {"url": "https://github.com/Significant-Gravitas/Auto-GPT/security/advisories/GHSA-x5gj-2chr-4ch6", "tags": ["Patch", "Third Party Advisory"], "source": "af854a3a-2127-422b-91ae-364da2661108"}], "vulnStatus": "Modified", "weaknesses": [{"type": "Secondary", "source": "security-advisories@github.com", "description": [{"lang": "en", "value": "CWE-94"}]}], "descriptions": [{"lang": "en", "value": "Auto-GPT is an experimental open-source application showcasing the capabilities of the GPT-4 language model. Running Auto-GPT version prior to 0.4.3 by cloning the git repo and executing `docker compose run auto-gpt` in the repo root uses a different docker-compose.yml file from the one suggested in the official docker set up instructions. The docker-compose.yml file located in the repo root mounts itself into the docker container without write protection. This means that if malicious custom python code is executed via the `execute_python_file` and `execute_python_code` commands, it can overwrite the docker-compose.yml file and abuse it to gain control of the host system the next time Auto-GPT is started. The issue has been patched in version 0.4.3."}], "lastModified": "2024-11-21T08:11:22.180", "configurations": [{"nodes": [{"negate": false, "cpeMatch": [{"criteria": "cpe:2.3:a:agpt:auto-gpt:*:*:*:*:*:*:*:*", "vulnerable": true, "matchCriteriaId": "10E8D9E9-E73C-4B20-989E-1D432F7ED3BB", "versionEndExcluding": "0.4.3"}], "operator": "OR"}]}], "sourceIdentifier": "security-advisories@github.com"}