CVE-2024-58399 — Vulnerability intelligence
—
Published:
- CVSS
- 6.9
- CISA KEV
- Not listed; not proof of no exploitation
Original source text (not a translation)
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.