Browse / Unsafe Model Loading and Supply Chain / CVE-2023-36281
langchain vulnerable to arbitrary code execution
- Class
- Unsafe Model Loading and Supply Chain (filed by a model that read the advisory)
- Technique
- Code and command execution
- Affected
- langchain (PyPI)
- CVSS
- CVSS:3.1/AV:N/AC:L/PR:N/UI:N/S:U/C:H/I:H/A:H
- EPSS
- 3.4% chance of exploitation in 30 days
How it works, in short
A crafted prompt JSON file passed to load_prompt can reach Python internals through template and __subclasses__ tricks, executing code when loaded. (Our summary, written by a model. The source text is below.)
Details
An issue in langchain v.0.0.171 allows a remote attacker to execute arbitrary code via the via the a json file to the load_prompt parameter. This is related to __subclasses__ or a template.
References
- https://nvd.nist.gov/vuln/detail/CVE-2023-36281
- https://github.com/hwchase17/langchain/issues/4394
- https://github.com/langchain-ai/langchain/pull/10252
- https://github.com/langchain-ai/langchain/commit/22abeb9f6cc555591bf8e92b5e328e43aa07ff6c
- https://aisec.today/LangChain-2e6244a313dd46139c5ef28cbcab9e55
- https://github.com/langchain-ai/langchain
- https://github.com/langchain-ai/langchain/releases/tag/v0.0.312
- https://github.com/pypa/advisory-database/tree/main/vulns/langchain/PYSEC-2023-151.yaml
Source: GitHub Advisory Database, used under CC BY 4.0.