- CVSS
- MEDIUM · 6.1v3.1CVSS:3.1/AV:L/AC:L/PR:N/UI:R/S:U/C:L/I:N/A:H
- Published
- 2026-10-27
- Weakness
- CWE-125
- Source
- nvd.nist.gov/vuln/detail/CVE-2024-58399
Description
llama.cpp before b2731 contains an out-of-bounds read vulnerability in llama_model_loader that allows attackers to read memory outside the mapped model file via crafted GGUF tensor offsets. Attackers can supply a crafted or truncated GGUF model file with arbitrary 64-bit tensor offsets to crash the process or load adjacent process memory as model weights.
References
- https://github.com/ggml-org/llama.cpp/blob/b2730/llama.cpp#L3002-L3004
- https://github.com/ggml-org/llama.cpp/commit/0ead1f1072fdc70720f92e008a294dc74a826b1d
- https://github.com/ggml-org/llama.cpp/issues/6774
- https://github.com/ggml-org/llama.cpp/pull/6885
- https://github.com/ggml-org/llama.cpp/releases/tag/b2731
- https://www.vulncheck.com/advisories/llama-cpp-before-b2731-out-of-bounds-read-via-gguf-tensor-offsets
How GTK Cyber trains on this
AI security training at GTK Cyber covers the LLM and ML-pipeline vulnerability classes that vulnerabilities like CVE-2024-58399 fall into. Our hands-on courses are taught by Charles Givre and other practitioners who break and defend production AI systems.