CRITICAL 9.8 PyPI
langchain vulnerable to arbitrary code execution
GHSA-7gfq-f96f-g85j · CVE-2023-36281 · PYSEC-2023-151
Published · Modified
AI SAST
Find this class of vulnerability in your own code
Corgea's AI-native static analysis detects vulnerabilities like this one across your repositories, ranks them by exploitability, and returns review-ready fixes.
Description
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
- ADVISORY https://nvd.nist.gov/vuln/detail/CVE-2023-36281
- WEB https://github.com/hwchase17/langchain/issues/4394
- WEB https://github.com/langchain-ai/langchain/pull/10252
- WEB https://github.com/langchain-ai/langchain/commit/22abeb9f6cc555591bf8e92b5e328e43aa07ff6c
- WEB https://aisec.today/LangChain-2e6244a313dd46139c5ef28cbcab9e55
- PACKAGE https://github.com/langchain-ai/langchain
- WEB https://github.com/langchain-ai/langchain/releases/tag/v0.0.312
- WEB https://github.com/pypa/advisory-database/tree/main/vulns/langchain/PYSEC-2023-151.yaml
Ready to move
Start Securing
Free, no credit card | First findings in minutes