GHSA-92j5-3459-qgp4

LangChain vulnerable to arbitrary code execution

Source: GitHub Advisory Database (reviewed) Critical CVE-2023-38896

Packages

Ecosystem	Package	Affected	Fixed in
PyPI	langchain	< 0.0.236	0.0.236

Details

As written in the advisory (Markdown source, shown as plain text).

An issue in Harrison Chase langchain before version 0.0.236 allows a remote attacker to execute arbitrary code via the `from_math_prompt` and `from_colored_object_prompt` functions.

References

External links from the advisory. They lead to third-party sites.

https://nvd.nist.gov/vuln/detail/CVE-2023-38896 advisory
https://github.com/hwchase17/langchain/issues/5872 web
https://github.com/hwchase17/langchain/pull/6003 web
https://github.com/langchain-ai/langchain/commit/8ba9835b925473655914f63822775679e03ea137 web
https://github.com/langchain-ai/langchain/commit/e294ba475a355feb95003ed8f1a2b99942509a9e web
https://github.com/langchain-ai/langchain package
https://github.com/pypa/advisory-database/tree/main/vulns/langchain/PYSEC-2023-146.yaml web
https://twitter.com/llm_sec/status/1668711587287375876 web