Cyber Resilience

CVE-2026-55443

Path Traversal in Langchain ≤ 1.3.9

Published
22 June 2026
Modified
26 June 2026
Patch / advisory
CVSS Score v3.1 5.1
Click a component to see what it means
Raw vectorCVSS:3.1/AV:L/AC:H/PR:N/UI:N/S:U/C:H/I:N/A:N
EPSS Score 0.0016 5th percentile
Risk Priority 38 floored blend · peak EPSS

Summary

CVE-2026-55443 is a medium-severity Path Traversal (CWE-22) vulnerability in Langchain Langchain. Its CVSS base score is 5.1 (Medium).

Operationally, exploitation aligns with the MITRE ATT&CK technique Path Interception (T1034); ranked at the 5th percentile by exploit likelihood (below the median); it is not currently listed in the CISA KEV catalog.

This vulnerability is AI-related — categorised as LLM Application Platforms.

The strongest mitigations our analysis identified map to AC-3 (Access Enforcement) and SI-10 (Information Input Validation) — see the control section below for these in your framework.

OWASP Top 10 for Web (2025)

EU & UK References

Vulnerability Data

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…

more

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.

CWE(s)

AI Security AnalysisAI

AI Category
LLM Application Platforms
Risk Domain
N/A
OWASP Top 10 for LLMs 2025
None mapped
Classification Reason
Matched keywords: langchain, llm, langchain, llm

Related Threats

MITRE ATT&CK Enterprise Techniques

T1034 Path Interception Persistence
**This technique has been deprecated.
T1190 Exploit Public-Facing Application Initial Access
Adversaries may attempt to exploit a weakness in an Internet-facing host or system to initially access a network.
T1547.009 Shortcut Modification Persistence
Adversaries may create or modify shortcuts that can execute a program during system boot or user login.
Derived from this CVE’s CWE(s) via the direct CWE→ATT&CK cross-walk.

CVEs Like This One

CVE-2024-3571Same product: Langchain Langchain
CVE-2024-28088Same product: Langchain Langchain
CVE-2026-34070Same vendor: Langchain
CVE-2026-24046Shared CWE-22, CWE-59
CVE-2026-44340Shared CWE-22, CWE-59
CVE-2024-7774Same vendor: Langchain
CVE-2026-34603Shared CWE-22, CWE-59
CVE-2026-47277Shared CWE-22, CWE-59
CVE-2022-21999Shared CWE-22, CWE-59
CVE-2026-33001Shared CWE-22, CWE-59

Affected Assets

langchain
langchain
≤ 1.3.9

Mitigating Controls

Control response

Prevent
Stop it (NIST 800-53)

Detect
Catch it (NIST detect / respond)

Harden
Shrink the surface (DISA STIG)

Validate
Prove the fix (OWASP ASVS)
  • V5.3.2
  • V15.4.2

Mitigating Controls (NIST 800-53 r5) AI

Enforces the intended directory access authorizations that path traversal would otherwise bypass.

Input validation directly neutralizes special path elements before pathname construction occurs.

Least privilege reduces the impact of any unauthorized file access obtained via traversal.

Mitigating Controls (NIST CSF 2.0) AI

Derived directly from the weakness types (CWEs) cited in the NVD entry via our AI-authored CWE→CSF cross-walk (authority under review) — links open the control.

PR.PS-06 mostly match
prevents

Secure SDLC practices directly require code to validate paths and avoid unsafe link following.

PR.PS-02 partial match
prevents

Patching/maintenance can remediate known path-traversal flaws in deployed software (partial prevention of exploitability) but does nothing to stop the coding defect from being introduced in the first place.

PR.AA-05 none match
prevents

PR.AA-05 defines and reviews access policies but does not address code-level pathname neutralization, so neither direction prevents CWE-22.

Mitigating Controls (ISO/IEC 27001:2022 Annex A) AI

Derived directly from the weakness types (CWEs) cited in the NVD entry via our AI-authored CWE→ISO cross-walk (authority under review) — links open the control.

finds

Security testing in development catches path traversal via static/dynamic analysis.

prevents

Secure SDLC mandates input validation and path sanitization that directly prevent path traversal.

prevents

Application security requirements include rules for safe file handling and canonicalization.

prevents

Secure architecture principles require least-privilege file access and directory isolation.

prevents

Secure coding standards explicitly forbid unsafe path construction and mandate safe APIs.

mitigates

Information access restriction limits which files an application may read or write.

References