CVE-2026-51882

Affects: LangChain

CVSS: CRITICAL · 9.1v3.1
CVSS:3.1/AV:N/AC:L/PR:N/UI:N/S:U/C:H/I:H/A:N
Published: 2026-10-01
Weakness: CWE-22
Source: nvd.nist.gov/vuln/detail/CVE-2026-51882

Description

The OpenAI-compatible file upload endpoint /v1/files in Langchain-Chatchat 0.3.0 is vulnerable to path traversal. An attacker can write files to arbitrary locations outside the openai_files directory by crafting malicious filenames.

References

https://gist.github.com/Ro1ME/f80ac458836b59adb9c6ceff3993f7f3
https://github.com/chatchat-space/Langchain-Chatchat/issues/5468
https://gist.github.com/Ro1ME/f80ac458836b59adb9c6ceff3993f7f3
https://github.com/chatchat-space/Langchain-Chatchat/issues/5468

How GTK Cyber trains on this

AI security training at GTK Cyber covers the LLM and ML-pipeline vulnerability classes that vulnerabilities like CVE-2026-51882 fall into. Our hands-on courses are taught by Charles Givre and other practitioners who break and defend production AI systems.

AI Red-Teaming course →·Browse MITRE ATLAS techniques

Related AI/LLM CVEs

CVE-2026-119408(HIGH)
CVE-2026-119978(HIGH)
CVE-2026-75128(CRITICAL)
CVE-2026-108748(MEDIUM)
CVE-2026-51883(CRITICAL)
CVE-2026-51884(CRITICAL)
CVE-2026-101861(MEDIUM)
CVE-2026-97869(MEDIUM)

AI security training, taught by people who do the work.

Hands-on courses on adversarial AI, prompt injection, and ML pipeline security.

Explore AI Red-Teaming