CVE-2026-133710 — Ggml-org Llama.cpp (b12556) — CWE-190
CVE-2026-133710 is a HIGH severity security vulnerability (CWE-190) (CVSS 8.5/10) affecting Ggml-org Llama.cpp (b12556). Technical vector analysis shows that an attacker can exploit this flaw via local access (AV:L) without authentication (PR:N) requiring user interaction, resulting in complete compromise of system confidentiality and integrity (C:H/I:H).
📄 Official NVD / MITRE Original Record Text
llama.cpp b11003 before b12556 contains an integer overflow in the hrm_text loader load_arch_hparams() that allows attackers to bypass the block count check using crafted GGUF metadata. Attackers can supply a GGUF model whose layer factors wrap modulo 2^32, causing load_arch_tensors() to write tensor pointers past model.layers, corrupting heap memory and potentially enabling code execution.
━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━
CVE-2026-133710
CVSS 8.5/10 · HIGH · 20.11.2026
CWE: CWE-190
Vector: CVSS:4.0/AV:L/AC:L/AT:N/PR:N/UI:P/VC:H/VI:H/VA:H/SC:N/SI:N/SA:N
━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━
🎯 WHAT IS THIS VULNERABILITY?
Summary: llama.cpp b11003 before b12556 contains an integer overflow in the hrm_text loader load_arch_hparams() that allows attackers to bypass the block count check using crafted GGUF metadata. Attackers can supply a GGUF model whose layer factors wrap modulo 2^32, causing load_arch_tensors() to write tensor pointers past model.layers, corrupting heap memory and potentially enabling code execution.
Affected: ggml-org:llama.cpp
⚡ ATTACK CHAIN
Local/physical access | no authentication required | user interaction required | low complexity.
🌍 REAL WORLD IMPACT
All confidential data readable/stealable; data can be modified or deleted; service can be completely taken down.
🛡️ REMEDIATION
→ Apply vendor security update for ggml-org:llama.cpp.
→ Add WAF rule, create IDS alert for anomalous traffic.
⚠️ URGENCY
⚠️ Planned maintenance (2 weeks).
────────────────────────────────────────
[Kural Tabanlı Otomatik Güvenlik Analizi]
FOFA Query