LangChain: Path traversal and sandbox escape in LangChain file-search middleware and loaders
CVE-2026-55443GHSA-gr75-jv2w-4656
What to do
Vendor fix available. Upgrade each affected package to the fixed version on its release line (langchain 1.3.9; langchain-anthropic 1.4.6), redeploy, then verify what is actually installed.
This page has no inventory attached, so it cannot say whether you are affected. A vendor fix is not proof that your deployment is fixed.
Affected packages
PyPI langchain
- Affected
- <= 1.3.8
- Fixed in
- 1.3.9
PyPI langchain-anthropic
- Affected
- <= 1.4.5
- Fixed in
- 1.4.6
Sources
- Open Source Vulnerabilities (OSV.dev), including the GitHub Advisory Database
OSV record GHSA-gr75-jv2w-4656 lists affected ranges: PyPI langchain >=0 =0 <1.4.6 (fixed)
VerifiedObserved Structured OSV record; GitHub-reviewed advisory.
- GitHub Advisory Database and maintainer security advisories on GitHub
GitHub-reviewed advisory GHSA-gr75-jv2w-4656 lists affected ranges: PyPI langchain >=0 =0 <=1.4.5
VerifiedObserved Structured GitHub Advisory Database record (type=reviewed) from the GitHub REST API.
Severity and exploitation
- Exploitation
- No confirmed exploitation recorded. Patch Next marks exploitation only from CISA KEV.
- CVSS
- 5.1 · CVSS:3.1/AV:L/AC:H/PR:N/UI:N/S:U/C:H/I:N/A:N
- EPSS
- CVE-2026-55443: 0.21% estimated exploitation activity in the next 30 days; percentile 11.27 (FIRST EPSS, 2026-11-03). This is a model estimate, not proof of exploitation or customer exposure.
Source description
As published by the source; long descriptions are shortened.
Summary 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. We have no evidence of this behavior being…
Dates and revisions
- Published by the source
- Last modified by the source
- Source last checked
- Revision 2 · amended ·
Amended from ghsa record GHSA-gr75-jv2w-4656
- Revision 1 · created ·
Published from osv record GHSA-gr75-jv2w-4656
Agent brief
Preview the exact text before you copy it. Commands are read-only suggestions; review them before running anything.
# Patch Next advisory brief: CVE-2026-55443 Advisory: LangChain: Path traversal and sandbox escape in LangChain file-search middleware and loaders IDs: CVE-2026-55443, GHSA-gr75-jv2w-4656 Record: https://patchnext.com/advisories/cve-2026-55443 (revision 2, source checked 26 Oct 2026, 13:46 UTC) Inventory: none attached. This brief comes from a public page and does not say whether any deployment is affected. Severity: Medium (CVSS 5.1) Exploitation: no confirmed exploitation recorded. Patch Next confirms exploitation only from CISA KEV. Vendor response: Vendor fix available; fixed versions by package: langchain 1.3.9; langchain-anthropic 1.4.6. A vendor fix does not mean a deployment is fixed. ## Affected components - PyPI langchain: affected <= 1.3.8; fixed in 1.3.9 - PyPI langchain-anthropic: affected <= 1.4.5; fixed in 1.4.6 ## Suggested inspection (read-only) - `python -m pip show langchain`: prints the installed version. Run with the environment that serves production active. - `python -m pip show langchain-anthropic`: prints the installed version. Run with the environment that serves production active. ## Supported action Upgrade each affected component to a fixed version on its release line. For a transitive dependency, upgrade the parent package or add an override or constraint, then regenerate the lockfile. Redeploy every environment that ran an affected version. ## Required regression checks - Run the test suite and a production build. - Exercise the features that depend on langchain, langchain-anthropic. - Repeat the inspection and confirm that only fixed versions remain installed. ## Rollback considerations - Keep the previous lockfile and deployment artifact. Rolling back reinstates the vulnerable version, so apply any documented mitigation while you fix forward. ## Unresolved questions - Which deployments run an affected version? - Exploitation status can change. Check again before lowering the priority. - Mark the work resolved only after the fixed version is verified in production. ## Sources - Verified: https://osv.dev/vulnerability/GHSA-gr75-jv2w-4656 (OSV record GHSA-gr75-jv2w-4656 lists affected ranges: PyPI langchain >=0 =0 <1.4.6 (fixed)) - Verified: https://github.com/advisories/GHSA-gr75-jv2w-4656 (GitHub-reviewed advisory GHSA-gr75-jv2w-4656 lists affected ranges: PyPI langchain >=0 =0 <=1.4.5) Commands are suggestions: review each one before running it.
Loading voting…