Skip to content
Fencer Vulns
medium 5.1

CVE-2026-55443 json

LangChain: Path traversal and sandbox escape in LangChain file-search middleware and loaders

published 2026-06-16 4 mo ago modified 2026-09-10 1 mo ago also EUVD-2026-38332 , GHSA-gr75-jv2w-4656 , PYSEC-2026-2192 , PYSEC-2026-2556

cvss
5.1
version 3.1, CNA
cisa kev
Not listed
not in CISA's catalog
epss
0.2%
EPSS 0.2% chance of exploitation in 30 days, percentile 11%
public exploits
0
none known

Summary

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.

Patch / fix

  • pypi langchain 1.3.9
  • pypi langchain-anthropic 1.4.6
  • langchain langchain 1.3.9
  • langchain langchain-anthropic 1.4.6
  • python-langchain-anthropic openSUSE Tumbleweed 1.7.5-1.1

opensuse advisories openSUSE-SU-2026:11946-1

Vendor advisories

What the vendors themselves say about their products: affected, fixed or not affected, and what to do.

red hat product security vex CVE-2026-55443 updated cvss 5.1

langchain: langchain-anthropic: LangChain: Information disclosure via improper path confinement

  • Red Hat Migration Toolkit for Applications 8 mta/mta-solution-server-rhel9
    affected: no fix available “Fix deferred”
  • Red Hat Ansible Automation Platform 2 ansible-automation-platform-24/lightspeed-rhel8, ansible-automation-platform-25/lightspeed-rhel8, ansible-automation-platform-25/lightspeed-chatbot-rhel8
    affected: no fix planned “Out of support scope”
  • Red Hat Enterprise Linux AI (RHEL AI) 3 rhelai3/bootc-cuda-rhel9, rhelai3/bootc-rocm-rhel9, rhelai3/bootc-gaudi-rhel9, rhelai3/disk-image-cuda-rhel9 Red Hat OpenShift AI (RHOAI) rhoai/odh-llama-stack-core-rhel9, rhoai/odh-trustyai-nemo-guardrails-server-rhel9
    affected: no fix available “Fix deferred”
  • Red Hat Exploit Intelligence exploit-intelligence/vulnerability-analysis-rhel9
    under investigation
  • Red Hat Ansible Automation Orchestrator 2026 ansible-automation-platform/automation-orchestrator-backend-rhel9 Red Hat OpenShift Lightspeed openshift-lightspeed/lightspeed-service-api-rhel9, openshift-lightspeed/lightspeed-agentic-sandbox-rhel9 Red Hat OpenShift AI (RHOAI) rhoai/odh-trustyai-garak-lls-provider-dsp-rhel9
    not affected: vulnerable code not present

Red Hat CSAF VEX © Red Hat, Inc., from https://security.access.redhat.com/data/csaf/v2/vex/; changed: reduced to product statuses and remediations. CC BY 4.0 · csaf

CISA SSVC

Exploitation
none
Automatable
no
Technical impact
partial
Assessed
4 mo ago

Exploit prediction

0.21% chance of exploitation in the next 30 days, higher than 11% of all scored CVEs (FIRST EPSS, 2026-11-08).

CVSS scores

assigned by version score vector
CNA 3.1 5.1 CVSS:3.1/AV:L/AC:H/PR:N/UI:N/S:U/C:H/I:N/A:N
GitHub 3.1 5.1 CVSS:3.1/AV:L/AC:H/PR:N/UI:N/S:U/C:H/I:N/A:N
NVD 3.1 5.5 CVSS:3.1/AV:L/AC:L/PR:L/UI:N/S:U/C:H/I:N/A:N
OSV 3.1 5.5 CVSS:3.1/AV:L/AC:L/PR:L/UI:N/S:U/C:H/I:N/A:N
OSV 3.1 5.1 CVSS:3.1/AV:L/AC:H/PR:N/UI:N/S:U/C:H/I:N/A:N

Affected packages

ecosystem package affected fixed in
pypi langchain
<1.3.9
1.3.9
pypi langchain-anthropic
<1.4.6
1.4.6

Affected products

  • langchain-ai langchain
  • langchain-ai langchain-anthropic

Classification

Weakness
  • CWE-22 Improper Limitation of a Pathname to a Restricted Directory
  • CWE-59 Improper Link Resolution Before File Access

References

Sources

Fencer Vulns keeps one entry per vulnerability: the CVE id wins, then GHSA, and records that alias each other are merged, except that two CVEs always keep separate entries. The same data is available as JSON.

CPEs and fixed versions use Anchore's correction of NVD's data: Added CPE configurations because not yet analyzed by NVD.