CVE-2024-58399 — llama_model_loader that — CWE-125
CVE-2024-58399 is a MEDIUM severity Memory Corruption / Buffer Overflow vulnerability (CWE-125) (CVSS 6.1/10) affecting llama_model_loader that. Technical vector analysis shows that an attacker can exploit this flaw via local access (AV:L) without authentication (PR:N) requiring user interaction, causing high-impact service disruption (A:H).
📄 Official NVD / MITRE Original Record Text
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.
━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━
CVE-2024-58399
CVSS 6.1/10 · MEDIUM · 27.10.2026
CWE: CWE-125
Vector: CVSS:3.1/AV:L/AC:L/PR:N/UI:R/S:U/C:L/I:N/A:H
━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━
🎯 WHAT IS THIS VULNERABILITY?
Summary: 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.
⚡ ATTACK CHAIN
Local/physical access | no authentication required | user interaction required | low complexity.
🌍 REAL WORLD IMPACT
Service can be completely taken down.
🛡️ REMEDIATION
→ Apply the vendor-released patch immediately.
→ Add WAF rule, create IDS alert for anomalous traffic.
⚠️ URGENCY
📋 Routine update cycle (30 days)
────────────────────────────────────────
[Kural Tabanlı Otomatik Güvenlik Analizi]