CVE-2026-33298
llama.cpp has a Heap Buffer Overflow via Integer Overflow in GGUF Tensor Parsing
HIGH 7.8
En bref
- Source
- NVD
- EPSS
- EPSS 0.50 % · centile 42 ()
- État
- PUBLISHED
- Publiée
- Mise à jour
- Attribuée par
- GitHub_M
- Statut NVD
- Analyzed
Description
llama.cpp is an inference of several LLM models in C/C++. Prior to b7824, an integer overflow vulnerability in the `ggml_nbytes` function allows an attacker to bypass memory validation by crafting a GGUF file with specific tensor dimensions. This causes `ggml_nbytes` to return a significantly smaller size than required (e.g., 4MB instead of Exabytes), leading to a heap-based buffer overflow when the application subsequently processes the tensor. This vulnerability allows potential Remote Code Execution (RCE) via memory corruption. b7824 contains a fix.
Faiblesses (CWE)
Références
Scores
| Version | Score | Vecteur | Évalué par |
|---|---|---|---|
| CVSS 3.1 | HIGH 7.8 | CVSS:3.1/AV:L/AC:L/PR:N/UI:R/S:U/C:H/I:H/A:H | GitHub_M |
| CVSS 3.1 | HIGH 7.8 | CVSS:3.1/AV:L/AC:L/PR:N/UI:R/S:U/C:H/I:H/A:H | NVD · security-advisories@github.com (Secondary) |
Références européennes
- ENISA EUVD · EUVD-2026-14668
- GCVE · GCVE-0-2026-33298
Configurations affectées (CPE NVD)
cpe:2.3:a:ggml:llama.cpp:*:*:*:*:*:*:*:*< b7824
Produits affectés
| Produit | Versions |
|---|---|
| ggml-org · llama.cpp | affected < b7824 |
Sources
| Source | Licence |
|---|---|
| CVE List (CVEProject cvelistV5) | CVE Program Terms of Use |
| EPSS (FIRST.org) | FIRST — attribution requested |
| ENISA EUVD | ENISA — reproduction authorised, source acknowledged |
| NVD (NIST) via fkie-cad/nvd-json-data-feeds | Public domain — this product uses data from the NVD API but is not endorsed or certified by the NVD |