9.3 CriticalCWE-502
CVE-2025-68664
LangChain serialization injection vulnerability enables secret extraction in dumps/loads APIs
langchain-ailangchain
Status
- Not in CISA KEV
Exploit probabilityEPSSchecked 25 Oct
43%probability of exploitation in the next 30 days
Higher than 99% of scored CVEs
SeverityCVSS
9.3Critical
Description NVD
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.
Coverage 2 articles · 2 outlets
See the full timelineShow as table
| Published (UTC) | Outlet | Headline |
|---|---|---|
| Fri 30 Jan · 19:45 UTC | Microsoft | Case study: Securing AI application supply chains |
| Fri 27 Mar · 09:24 UTC | The Hacker News | LangChain, LangGraph Flaws Expose Files, Secrets, Databases in Widely Used AI Frameworks |
- LangChain, LangGraph Flaws Expose Files, Secrets, Databases in Widely Used AI FrameworksThe Hacker News · mentions it in passing
- Case study: Securing AI application supply chainsMicrosoft · first in our coverage