Free AI Safety Workshop — in collaboration with explainx.aiSave your seat
AgentbeamBeta
AI agent vulnerability · LangChain

CVE-2023-36281: langchain vulnerable to arbitrary code execution

criticalCVSS 4.0 9.3 · 3.1 9.8GHSA-7gfq-f96f-g85j

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 loadprompt parameter. This is related to subclasses or a template.

Published Aug 22, 2023 · Updated Sep 30, 2024

Affected packages

langchain

Ecosystem
PyPI
Affected
< 0.0.312
Fixed in
0.0.312
Check
pip show langchain

Advisory details

From the GitHub Advisory Database (CC BY 4.0).

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.

Credited to eyurtsev.

References

How this page is made: the data panel comes from the GitHub Advisory Database, CISA’s KEV catalog, the NVD and FIRST EPSS, and updates twice a day. No analysis has been written for this entry yet. Methodology

More LangChain vulnerabilities

All LangChain entries