Is CVE-2026-55443 exploited in the wild?

No. Junglewise Threat Intelligence has no report of CVE-2026-55443 being exploited in the wild.

How severe is CVE-2026-55443?

Medium severity, with a CVSS score of 5.1, published 22 June 2026.

Which products and versions are affected?

langchain (PyPI) ECOSYSTEM:introduced=0,fixed=1.3.9; langchain-anthropic (PyPI) ECOSYSTEM:introduced=0,fixed=1.4.6.

Is there a fix for CVE-2026-55443?

Yes. langchain (PyPI): upgrade to 1.3.9 or later; langchain-anthropic (PyPI): upgrade to 1.4.6 or later. Junglewise finds every place you run it, drafts the upgrade and applies it once you approve.

How is CVE-2026-55443 attacked?

It is attacked with local access, in a software library.

Am I affected by CVE-2026-55443?

Check whether you run langchain (PyPI) or langchain-anthropic (PyPI) at an affected version. Junglewise does that check for you around the clock: connect your code, cloud and domains, and it matches new vulnerabilities like this one against what you actually run and tells you when one reaches you.

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

CVE-2026-55443 · Severity: medium · CVSS 5.1 · Published 2026-06-22

LangChain is a popular framework used to build applications powered by Artificial Intelligence and Large Language Models (LLMs). A security flaw in how the framework handles file paths allows an attacker—potentially by tricking an AI agent with malicious input—to access sensitive files on the underlying server that should be off-limits. This could lead to the unauthorized disclosure of private data or system configuration files, though it requires specific conditions to exploit.

Technologies: langchain (PyPI). Vendors: PyPI.

Quick answers

Is CVE-2026-55443 exploited in the wild?: No. Junglewise Threat Intelligence has no report of CVE-2026-55443 being exploited in the wild.
How severe is CVE-2026-55443?: Medium severity, with a CVSS score of 5.1, published 22 June 2026.
Which products and versions are affected?: langchain (PyPI) ECOSYSTEM:introduced=0,fixed=1.3.9; langchain-anthropic (PyPI) ECOSYSTEM:introduced=0,fixed=1.4.6.
Is there a fix for CVE-2026-55443?: Yes. langchain (PyPI): upgrade to 1.3.9 or later; langchain-anthropic (PyPI): upgrade to 1.4.6 or later. Junglewise finds every place you run it, drafts the upgrade and applies it once you approve.
How is CVE-2026-55443 attacked?: It is attacked with local access, in a software library.
Am I affected by CVE-2026-55443?: Check whether you run langchain (PyPI) or langchain-anthropic (PyPI) at an affected version. Junglewise does that check for you around the clock: connect your code, cloud and domains, and it matches new vulnerabilities like this one against what you actually run and tells you when one reaches you.

How to fix

langchain (PyPI): upgrade to 1.3.9 or later
```
pip install "langchain>=1.3.9"
```
langchain-anthropic (PyPI): upgrade to 1.4.6 or later
```
pip install "langchain-anthropic>=1.4.6"
```

Technical details

Multiple components in LangChain, including file-search middleware and configuration loaders, fail to consistently canonicalize and validate filesystem paths against a trusted root directory. The vulnerability stems from improper handling of glob patterns, symlinks, and string-prefix authorization checks that lack path-segment boundaries (CWE-22, CWE-59). An attacker can exploit this by providing untrusted input to an LLM or agent that influences path resolution, leading to arbitrary file read outside the intended sandbox. The issue is mitigated in LangChain 1.3.9 and LangChain-Anthropic 1.4.6 by enforcing path normalization and strict containment checks.

Affected products

langchain-ai langchain < 1.3.9
langchain-ai langchain-anthropic < 1.4.6

Identifiers

CVE-2026-55443
GHSA-gr75-jv2w-4656
PYSEC-2026-2192
PYSEC-2026-2556

Timeline

2026-06-12: patched: Fix committed to repository
2026-06-22: disclosed: Security advisory published

References

This page as Markdown. Free to reuse under CC BY 4.0 with a link back.