CVE-2025-68664
LangChain serialization injection vulnerability enables secret extraction in dumps/loads APIs
HIGH 8.2EPSS 42.9%
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
- langchain-ai · langchain
- CVSS v3.1 NVD
- 8.2 HIGH
CVSS:3.1/AV:N/AC:L/PR:N/UI:N/S:U/C:H/I:L/A:N - CVSS v3.1 GITHUB
- 9.3 CRITICAL
CVSS:3.1/AV:N/AC:L/PR:N/UI:N/S:C/C:H/I:L/A:N - EPSS
- 42.93% chance of exploitation in the next 30 days, 99th percentile
- Published
- 2025-12-23
- Updated
- 2025-12-24
Proof-of-concept exploits (3)
- Ak-cybe/CVE-2025-68664-LangGrinch-PoC3★ · 2025-12-27
- ssoranno-lacework/LangGrinch_Vuln_Example0★ · 2026-04-22
- unhackable-demobeta/LangGrinch_Vuln_Example0★ · 2026-05-08
ExploitDB entries (1)
Security advisories
- langchain-ai/langchain/security/advisories/GHSA-c67j-w6g6-q2cm
- advisories/GHSA-c67j-w6g6-q2cm
- langchain-ai/langchain/pull/34455