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
- Oct 15, 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
A 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.
Technical analysis of the LangChain serialization injection vulnerability CVE-2025-68664.
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.