CVE-2024-58399 | 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.
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.
- 🔗 github.com/ggml-org/llama.cpp/issues/6774
- 🔗 github.com/ggml-org/llama.cpp/pull/6885
- 🔗 github.com/ggml-org/llama.cpp/commit/0ead1f1072fdc70…
- 🔗 github.com/ggml-org/llama.cpp/blob/b2730/llama.cpp
- 🔗 github.com/ggml-org/llama.cpp/releases/tag/b2731
- 🔗 www.vulncheck.com/advisories/llama-cpp-before-b2731-out-of-…
Zero-Day & Vulnerability Intelligence Hub
Echtzeit-Tracking mit EPSS Exploit-Wahrscheinlichkeiten, Angriffsvektor-Decodern und KI-Patch-Anleitungen.
📊 Historien-Charts — Criticals-Trend · Vendors · EPSS-Verteilung
| Tier | CVEs | Anteil |
|---|---|---|
| ≥90 % | 743 | 0,2 % |
| ≥50 % | 3.223 | 0,8 % |
| ≥10 % | 22.075 | 5,8 % |
| <10 % | 354.688 | 93,2 % |
CVE-2024-58399 | 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.
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 m