What’s Vulnerable › Vulnerabilities

CVE-2024-58399: llama.cpp before b2731 Out-of-Bounds Read via GGUF Tensor Offsets

• Severity: medium (CVSS 6.1 v3.1)
• Exploited in the wild: not listed in CISA KEV
• EPSS: 0.1% probability of exploitation in the next 30 days
• Public exploit or detection template: none known
• Published: 2026-10-27 · updated 2026-10-27
• Weakness: CWE-125

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.

Affected products

• ggml-org llama.cpp: from b1046 before b2731 — fixed in b2731

How to fix

Upgrade to a fixed version: ggml-org llama.cpp b2731. Check the vendor advisory for mitigations.

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

Get alerted when CVE-2024-58399 or the next vulnerability affects your stack