CVE-2026-33298
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.
Does this matter?
High impact if exploited, but EPSS currently rates exploitation as unlikely (0.48%). Schedule it in the normal patch cycle and watch for a rise in EPSS or a public exploit.
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.
- CVSS 3.1
- 7.8 HIGHCVSS:3.1/AV:L/AC:L/PR:N/UI:R/S:U/C:H/I:H/A:H
- EPSS
- 0.48% probability · 40th percentile
- CISA KEV
- Not listed
- Weakness
- CWE-122, CWE-190
- Affected
- ggml/llama.cpp
- Source
- security-advisories@github.com
References
- https://github.com/ggml-org/llama.cpp/releases/tag/b7824Release Notes
- https://github.com/ggml-org/llama.cpp/security/advisories/GHSA-96jg-mvhq-q7q7Exploit, Vendor Advisory
Source: NVD record, EPSS from FIRST.org, KEV from CISA. Refreshed daily.