CVE-2025-68664
LangChain serialization injection vulnerability enables secret extraction in dumps/loads APIs
- Published
- Dec 23, 2025
- Updated
- Dec 24, 2025
- Assigning CNA
- GitHub_M
- Evidence observed
- Apr 29, 2026
Primary CVSS
nvd · CVSS 3.1
CVSS:3.1/AV:N/AC:L/PR:N/UI:N/S:C/C:H/I:L/A:NModerate · next 30 days
- Percentile
- 98.7%
- Model date
- Sep 21, 2026
EPSS is a statistical estimate, not a certainty or a measure of impact. Combine it with CVSS, KEV status, exposure and your environment.
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.
Sources
4A testing framework to identify and demonstrate deserialization vulnerabilities in LangChain Core (<0.3.81). Educational use only
- CVE-2025-68664Research
Detailed disclosure of CVE-2025-68664, a critical deserialization vulnerability in LangChain core allowing secret exfiltration and potential RCE via crafted prompts and serialization flows.
Responsible use
Use vulnerability information only on systems you own or are authorized to test. Kitploit links to public research metadata and does not store exploit code or malicious payloads.