CVE-2025-68664PYSEC-2026-373GHSA-C67J-W6G6-Q2CM
LangChain serialization injection vulnerability enables secret extraction in dumps/loads APIs
- Published
- Last modified
- Where the record stands: published, rejected by its publisher, or superseded by another id.What do these mean? →
- published
- Whether CISA lists it in its Known Exploited Vulnerabilities catalog: proof that attackers are using it.What do these mean? →
- Not listed in CISA KEV
- Fix
- Fixed in 1.2.5, 0.3.81
- Whether working attack code is public (Exploit-DB, Metasploit, Nuclei or GitHub). Public code makes attacks easier.What do these mean? →
- None on Exploit-DB, Metasploit or GitHub
Summary
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.
Timeline
- CVE published
- Record last updated
- EPSS reached 10%
FIRST estimates at least a 10% chance of exploitation in the next 30 days
Affected versions
- langchain-ai langchain
From 1.0.0 · fixed in 1.2.5; fixed in 0.3.81
- langchain-corePyPI
From 1.0.0 · fixed in 1.2.5
- langchain-corePyPI
fixed in 0.3.81