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

CVE-2025-68664

CRITICAL

LangChain serialization injection vulnerability enables secret extraction in dumps/loads APIs

Also known asGHSA-c67j-w6g6-q2cm
Published
Dec 23, 2025
Updated
Apr 10, 2026
Affected
2 pkgs
Patched
2 / 2
Exploits
2 known

EPSS Exploitation Probability

via FIRST.org ↗
13.8%probability of exploitation in next 30 days
Moderate Risk96th percentile+11.57%
0.00%5.99%12.0%18.0%0.1%13.8%Jan 26Apr 26Jun 26

EPSS (Exploit Prediction Scoring System) is a daily probability model maintained by FIRST.org. It estimates the likelihood a CVE will be exploited in production environments within the next 30 days, derived from real-world threat intelligence signals.

Blast Radius

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 versions 0.3.81 and 1.2.5, a serialization injection vulnerability exists in LangChain's dumps() and dumpd() functions. The functions do not escape dictionaries with 'lc' keys when serializing free-form dictionaries. The 'lc' key is used internally by LangChain to mark serialized objects. When user-controlled data contains this key structure, it is treated as a legitimate LangChain object during deserialization rather than plain user data. This issue has been patched in versions 0.3.81 and 1.2.5.

Affected Packages

2 total 2 fixed
EcosystemPackageVulnerable rangeFix
🐍PyPIlangchain-core1.0.0&&< 1.2.51.2.5
🐍PyPIlangchain-coreall versions0.3.81
Exploits & PoCs
2

Research use only. For defensive security, authorized penetration testing, and academic research only. Never execute exploit code against systems without explicit written authorization.

EDB-52514webappsmultiple

LangChain Core 1.2.4 - SSTI/RCE

by banyamer · Apr 29, 2026

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 1.2.5 or later, then make sure no transitive (indirect) dependency still pins the vulnerable range — O3 confirms CVE-2025-68664 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-2025-68664 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-2025-68664. 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 versions 0.3.81 and 1.2.5, a serialization injection vulnerability exists in LangChain's dumps() and dumpd() functions. The functions do not escape dictionaries with 'lc' keys when serializing free-form dictionaries. The 'lc' key is used internally by LangChain to mark serialized objects. When user-controlled data contains this key structure, it is treated as a legitimate LangChain object during deserialization rather than plain user data. This issue has been patched in versions 0.3.81 and 1.2.5.
O3 Security · Impact-Aware SCA

Is CVE-2025-68664 in your dependencies?

O3 detects CVE-2025-68664 across PyPI dependencies and uses function-level reachability to confirm whether the vulnerable code path is actually reachable — not just present. No false positives.