Browse / Tool and Agent Misuse / CVE-2024-38459
langchain_experimental Code Execution via Python REPL access
- Class
- Tool and Agent Misuse (filed by a model that read the advisory)
- Technique
- Code and command execution
- Affected
- langchain-experimental (PyPI)
- CVSS
- CVSS:3.1/AV:L/AC:L/PR:N/UI:R/S:U/C:H/I:H/A:H
- EPSS
- 0.2% chance of exploitation in 30 days
How it works, in short
The Python REPL tool is available without an explicit opt-in, so an agent can run arbitrary Python code on the host. (Our summary, written by a model. The source text is below.)
Details
langchain_experimental (aka LangChain Experimental) before 0.0.61 for LangChain provides Python REPL access without an opt-in step. NOTE; this issue exists because of an incomplete fix for CVE-2024-27444.
References
- https://nvd.nist.gov/vuln/detail/CVE-2024-38459
- https://github.com/langchain-ai/langchain/pull/22860
- https://github.com/langchain-ai/langchain/commit/ce0b0f22a175139df8f41cdcfb4d2af411112009
- https://github.com/langchain-ai/langchain
- https://github.com/langchain-ai/langchain/compare/langchain-experimental==0.0.60...langchain-experimental==0.0.61
- https://github.com/pypa/advisory-database/tree/main/vulns/langchain-experimental/PYSEC-2024-53.yaml
Source: GitHub Advisory Database, used under CC BY 4.0.