{"id":"CVE-2026-55443","aliases":["GHSA-gr75-jv2w-4656","PYSEC-2026-2192","PYSEC-2026-2556"],"title":"LangChain: Path traversal and sandbox escape in LangChain file-search middleware and loaders","summary":"LangChain: Path traversal and sandbox escape in LangChain file-search middleware and loaders","severity":"medium","cvss":5.1,"cvssVector":"CVSS:3.1/AV:L/AC:H/PR:N/UI:N/S:U/C:H/I:N/A:N","vendor":"langchain","product":"langchain","ecosystem":"pip","affected":["langchain < 1.3.9","langchain-anthropic < 1.4.6"],"patched":["langchain 1.3.9","langchain-anthropic 1.4.6"],"published":"2026-06-16","updated":"2026-09-10","sourceUpdated":"2026-09-10T03:51:08.737829576Z","source":"OSV","sourceUrl":"https://osv.dev/vulnerability/GHSA-gr75-jv2w-4656","references":[{"url":"https://github.com/langchain-ai/langchain/security/advisories/GHSA-gr75-jv2w-4656"},{"url":"https://nvd.nist.gov/vuln/detail/CVE-2026-55443"},{"url":"https://github.com/langchain-ai/langchain/commit/dcaf7795a3e6590af55c3ff7bda6add6355e9ea6"},{"url":"https://github.com/langchain-ai/langchain"}],"tags":["osv","pip"],"epss":0.0021,"epssPercentile":0.11527,"ingestedAt":"2026-07-08T18:25:49.770Z","slug":"CVE-2026-55443","body":"## Overview\n\n## Summary\n\nSeveral 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 triggered in the wild.\n\n## Affected users / systems\n\nYou may be affected if you expose an agent with filesystem-search middleware over a directory and accept prompts or retrieved content influenced by untrusted sources; load prompt or chain/agent configuration from untrusted or shared sources; or rely on path-prefix restrictions to confine tool file access. Callers that confine these components to fully trusted inputs and first-party configuration are not affected.\n\n## Impact\n\n- Confidentiality: disclosure of file contents outside the intended root/sandbox.\n- Authorization: path-prefix bypass can grant access to sibling resources beyond the intended subtree.\n\n## Patches / mitigation\n\nThe affected components will canonicalize candidate paths (resolving symlinks) and verify the resolved real path remains within the configured root before reading or returning it; search patterns will be normalized so they cannot escape the root; configuration loaders will confine resolved path fields and reject symlink escapes unless the caller explicitly opts in to dangerous loading; and path-prefix checks will enforce a path-segment boundary. Path validation will be made operating-system-portable.\n\n## Compatibility\n\nCallers that already pass only in-root paths, validated configuration, and trusted search inputs see no behavioral change. Callers that intentionally reference external paths can opt in via the existing dangerous-loading flag.\n\n## Operational guidance\n\nConfine filesystem-backed agent tools to a dedicated directory and prefer running them sandboxed/containerized; validate path and identifier inputs where untrusted input enters; do not enable dangerous loading for configuration whose origin you do not control.\n\n## LangSmith / hosted deployments note\n\nThis issue concerns library components executed by agents.\n\n## Affected packages\n\n- `langchain < 1.3.9`\n- `langchain-anthropic < 1.4.6`\n\n## Remediation\n\nUpgrade to a patched release:\n\n- `langchain 1.3.9`\n- `langchain-anthropic 1.4.6`","depth":"sunlit","depthScore":28,"depthScoreParts":{"impact":28.1,"likelihood":0,"exploitation":0,"ransomware":0},"changes":[]}