CVE-2024-58399
6.1 MEDIUMpublic exploit availablePublished 2026-10-27 · Updated 2026-10-27
AI analysis for this CVE has not been generated yet. Raw NVD data is shown below.
NVD 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.
CVSS vector
CVSS:3.1/AV:L/AC:L/PR:N/UI:R/S:U/C:L/I:N/A:H
Weaknesses
CWE-125
Public exploit & PoC 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
All 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
Source data: NVD (nvd.nist.gov), public domain. Exploit-DB.ai adds local AI analysis for defensive use only.
Related CVEs
- LOWCVE-2024-58392PoC
- MEDIUMCVE-2024-58397PoC
- MEDIUMCVE-2025-60494PoC
- MEDIUMCVE-2025-71438PoC
- MEDIUMCVE-2025-71439PoC
- MEDIUMCVE-2026-100126
- MEDIUMCVE-2026-100130
- MEDIUMCVE-2026-100131
Related by shared AI tags and CWE weakness class. Browse the full archive.