CVE-2026-34070
LangChain Core has Path Traversal vulnerabilites in legacy `load_prompt` functions
HIGH 7.5EPSS 1.2%
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.
- Affected
- langchain-ai · langchain
- CVSS v3.1 CNA
- 7.5 HIGH
CVSS:3.1/AV:N/AC:L/PR:N/UI:N/S:U/C:H/I:N/A:N - EPSS
- 1.21% chance of exploitation in the next 30 days, 68th percentile
- Published
- 2026-03-31
- Updated
- 2026-08-25
Proof-of-concept exploits (1)
- Rickidevs/CVE-2026-340700★ · 2026-03-26
Security advisories
- langchain-ai/langchain/security/advisories/GHSA-qh6h-p6c9-ff54
- advisories/GHSA-qh6h-p6c9-ff54
- langchain-ai/langchain/commit/27add913474e01e33bededf4096151130ba0d47c