LangChain through 0.1.10 allows ../ directory traversal by an actor who is able to control the final part of the path parameter in a load_chain call. This bypasses the intended behavior of loading configurations only from the hwchase17/langchain-hub GitHub repository. The outcome can be disclosure of an API key for a large language model online service, or remote code execution. (A patch is available as of release 0.1.29 of langchain-core.)
References
| Link | Resource |
|---|---|
| https://github.com/PinkDraconian/PoC-Langchain-RCE/blob/main/README.md | Exploit |
| https://github.com/langchain-ai/langchain/blob/f96dd57501131840b713ed7c2e86cbf1ddc2761f/libs/core/langchain_core/utils/loading.py | Product Third Party Advisory |
| https://github.com/langchain-ai/langchain/pull/18600 | Exploit Issue Tracking Patch |
| https://github.com/PinkDraconian/PoC-Langchain-RCE/blob/main/README.md | Exploit Third Party Advisory |
| https://github.com/langchain-ai/langchain/blob/f96dd57501131840b713ed7c2e86cbf1ddc2761f/libs/core/langchain_core/utils/loading.py | Product |
| https://github.com/langchain-ai/langchain/pull/18600 | Exploit Issue Tracking Patch |
Configurations
History
No history.
Information
Published : 2024-03-04 00:15
Updated : 2025-01-08 16:13
NVD link : CVE-2024-28088
Mitre link : CVE-2024-28088
CVE.ORG link : CVE-2024-28088
JSON object : View
Products Affected
langchain
- langchain
