Vulnerability · Published Oct 27, 2026 · Assigned by VulnCheck
CVE-2024-58399llama.cpp before b2731 Out-of-Bounds Read via GGUF Tensor Offsets
Medium 6.1
In plain English
A medium-severity out-of-bounds read in llama.cpp from ggml-org. There are no confirmed reports of exploitation so far. The chance it is exploited in the next 30 days is estimated at 0.1% (higher than 2% of all known vulnerabilities).
Severity (CVSS 3.1)6.1Medium
Exploit odds (30 days)0.1%top 98.1% of all CVEs
Exploited in the wildNo reportsCISA SSVC: none
Attack toolingNoneno public tooling known
Official 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 packages & fixed versions
| Ecosystem | Package | Fixed in | Advisory |
|---|---|---|---|
| Ubuntu:26.04:LTS | llama.cpp | no fix listed | UBUNTU-CVE-2024-58399 |
| Ubuntu:26.10 | llama.cpp | no fix listed | UBUNTU-CVE-2024-58399 |
Affected products (as reported)
Weakness: CWE-125 · Vector: CVSS:3.1/AV:L/AC:L/PR:N/UI:R/S:U/C:L/I:N/A:H
References
- https://github.com/ggml-org/llama.cpp/issues/6774 issue-tracking
- https://github.com/ggml-org/llama.cpp/pull/6885 patch, issue-tracking
- https://github.com/ggml-org/llama.cpp/commit/0ead1f1072fdc70720f92e008a294dc74a826b1d patch
- https://github.com/ggml-org/llama.cpp/blob/b2730/llama.cpp#L3002-L3004 technical-description
- llama.cpp b2731 Release Notes release-notes
- VulnCheck Advisory: llama.cpp before b2731 Out-of-Bounds Read via GGUF Tensor Offsets third-party-advisory