Description
LangChain is a framework for building agents and LLM-powered applications. Prior to version 1.2.22, multiple functions in langchain_core.prompts.loading read files from paths embedded in deserialized config dicts without validating against directory traversal or absolute path injection. When an application passes user-influenced prompt configurations to load_prompt() or load_prompt_from_config(), an attacker can read arbitrary files on the host filesystem, constrained only by file-extension checks (.txt for templates, .json/.yaml for examples). This issue has been patched in version 1.2.22.
Problem types
CWE-22: Improper Limitation of a Pathname to a Restricted Directory ('Path Traversal')
Product status
References
github.com/...gchain/security/advisories/GHSA-qh6h-p6c9-ff54
github.com/...gchain/security/advisories/GHSA-qh6h-p6c9-ff54
github.com/...ommit/27add913474e01e33bededf4096151130ba0d47c
github.com/.../langchain/releases/tag/langchain-core==1.2.22