Host code execution via unsanitized basename traversal
Published Jul 13, 2023 · Updated Oct 30, 2024
Path traversal in Significant Gravitas AutoGPT before 0.4.3 allows local users to execute host code after command approval and restart. The execute_python_code command writes LLM-supplied code to a filename derived from an unsanitized basename, allowing traversal outside the workspace to overwrite autogpt/main.py. Exploitation requires a direct-host installation, approval of the generated command unless continuous mode is enabled, and a later AutoGPT restart; the resulting Python runs outside the temporary Docker sandbox.
Summary
What happened
Path traversal in Significant Gravitas AutoGPT before 0.4.3 allows local users to execute host code after command approval and restart. The execute_python_code command writes LLM-supplied code to a filename derived from an unsanitized basename, allowing traversal outside the workspace to overwrite autogpt/main.py. Exploitation requires a direct-host installation, approval of the generated command unless continuous mode is enabled, and a later AutoGPT restart; the resulting Python runs outside the temporary Docker sandbox.
The record
- CVE
- CVE-2023-37274
- Published
- Jul 13, 2023
- Updated
- Oct 30, 2024
- Vendor
- Significant Gravitas
- Product
- AutoGPT
- Classifications
- CWE-94, T1059.006
- Attack vector
- local
- Privileges
- Unavailable
Timeline
How it unfolded
- Jul 13, 2023CVE publishedPublication date reported by the CVE source.
- Oct 30, 2024Record updatedLatest update available in the CVE record.
Exploitability
Present is not the same as exploitable
Compare your product and version with the public record. A matching version still requires validation against your environment.
Is a vulnerable build present?
Compare these published version ranges with your installed build and any vendor patches.
- Affected versionversion=< 0.4.3
What conditions does exploitation require?
What is affected?
Published CVSS scores
CVSS describes severity. EPSS estimates exploitation probability.
Attacks
What attackers are doing with it
Daily unique IPs observed by Shadowserver honeypots for known exploited vulnerabilities (KEVs). Missing observations do not establish an absence of attacks.
Weakness, pattern, technique
Public exploit references
- AutoGPT path-traversal sandbox-escape demonstrationfunctional · demonstrated
Labels summarize the accepted research assessment. They do not indicate a test against your environment.
Technologies
Your stack
See the directory against your own environment.
Your stack
Check the software in your environment
Book a demo to see how Hinoki identifies affected software and validates exploitability in your environment.
Book a demo