Your RSA-2048 keys break in 2030. Find every one of them before attackers do.
🐍 PyPI

CVE-2026-44843

HIGH

CVE-2026-44843 is a high-severity (CVSS 8.2) remote code execution vulnerability in langchain-core. O3 Security confirms whether CVE-2026-44843 is actually reachable in your code before you act, and blocks exploitation at runtime until you patch.

LangChain: Unsafe deserialization of attacker-controlled LangChain objects through overly broad `load()` allowlists

Also known asGHSA-pjwx-r37v-7724PYSEC-2026-2564
Published
May 26, 2026
Updated
Aug 7, 2026
Affected
2 pkgs
Patched
2 / 2
Exploits
None indexed

Real-World Exposure

2 pkgs affected
🐍langchain-core🐍langchain-core

Real-time download stats are indexed for npm and PyPI packages. This vulnerability affects PyPI packages — download data is not available via public APIs for these ecosystems.

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.

Affected Packages

2 total 2 fixed
EcosystemPackageVulnerable rangeFix
🐍PyPIlangchain-core1.0.0&&< 1.3.31.3.3
🐍PyPIlangchain-coreall versions0.3.85

Detection & mitigation playbook

Open-source dependency
  1. Detect

    Scan your dependency tree (package-lock.json, pnpm-lock.yaml, requirements.txt, go.sum, etc.) for langchain-core. O3's reachability analysis confirms whether the vulnerable code path is actually invoked in your application, so you act on real exposure instead of every transitive match.

  2. Fix

    Update langchain-core to 1.3.3 or later, then make sure no transitive (indirect) dependency still pins the vulnerable range — O3 confirms CVE-2026-44843 is resolved across your whole dependency graph.

  3. Workarounds

    If you can't upgrade right away: gate or disable the affected feature, validate untrusted input at the boundary, and avoid passing attacker-controlled data into the vulnerable path. O3's runtime protection blocks exploitation in production as an interim safeguard until the upgrade lands.

  4. How O3 protects you

    O3 pinpoints whether CVE-2026-44843 is reachable in your code and exactly where to fix it, then blocks exploitation in production at runtime until the patched version is deployed.

Tailored to CVE-2026-44843. Runtime protection reduces exposure until a permanent patch is applied and verified — it complements patching, it doesn't replace it.

Frequently Asked Questions

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 tr
O3 Security · Impact-Aware SCA

Is CVE-2026-44843 in your dependencies?

O3 detects CVE-2026-44843 across PyPI dependencies and uses function-level reachability to confirm whether the vulnerable code path is actually reachable — not just present. No false positives.