CVE-2025-45150

Affects: LangChain

CVSS: CRITICAL · 9.8v3.1
CVSS:3.1/AV:N/AC:L/PR:N/UI:N/S:U/C:H/I:H/A:H
Published: 2025-08-01
Weakness: CWE-732
Source: nvd.nist.gov/vuln/detail/CVE-2025-45150

Description

Insecure permissions in LangChain-ChatGLM-Webui commit ef829 allows attackers to arbitrarily view and download sensitive files via supplying a crafted request.

References

http://langchain-chatglm-webui.com
https://gist.github.com/ycshao12/69a48551cc6c9cc69153d137afe9ecef
https://github.com/X-D-Lab/LangChain-ChatGLM-Webui

How GTK Cyber trains on this

AI security training at GTK Cyber covers the LLM and ML-pipeline vulnerability classes that vulnerabilities like CVE-2025-45150 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-2026-55443(MEDIUM)
CVE-2026-45134(HIGH)
CVE-2026-44843(HIGH)
CVE-2026-45401(HIGH)
CVE-2026-7844(MEDIUM)
CVE-2026-41481(MEDIUM)
CVE-2026-30617(HIGH)
CVE-2026-40087(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