CVE-2026-52131

Affects: llama.cpp

CVSS: HIGH · 7.5v3.1
CVSS:3.1/AV:N/AC:L/PR:N/UI:N/S:U/C:H/I:N/A:N
Published: 2026-09-01
Weakness: CWE-617
Source: nvd.nist.gov/vuln/detail/CVE-2026-52131

Description

llama.cpp b5693 and before has a Reachable Assertion via the gguf_reader::read function.

References

https://blog.ph4nt0m.xyz/ko/cves/cve-2026-52130/
https://github.com/ggml-org/llama.cpp

How GTK Cyber trains on this

AI security training at GTK Cyber covers the LLM and ML-pipeline vulnerability classes that vulnerabilities like CVE-2026-52131 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-2026-86317(MEDIUM)
CVE-2026-52130(HIGH)
CVE-2026-52132(HIGH)
CVE-2026-78148(MEDIUM)
CVE-2026-78147(HIGH)
CVE-2026-43622(HIGH)
CVE-2026-43627(HIGH)
CVE-2026-43628(HIGH)

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