CVE-2026-33298 json
llama.cpp has a Heap Buffer Overflow via Integer Overflow in GGUF Tensor Parsing
published 2026-03-24 7 mo ago modified 2026-06-17 4 mo ago also EUVD-2026-14668
- cvss
- 7.8
- version 3.1, CNA
- cisa kev
- Not listed
- not in CISA's catalog
- epss
- 0.5%
- EPSS 0.5% chance of exploitation in 30 days, percentile 42%
- public exploits
- 0
- none known
Summary
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.
Patch / fix
Vendor advisories
What the vendors themselves say about their products: affected, fixed or not affected, and what to do.
red hat product security vex CVE-2026-33298 updated cvss 7.8
llama.cpp: llama.cpp: Remote Code Execution vulnerability due to integer overflow in GGUF file processing
-
Red Hat All currently supported Red Hat productsnot affected: vulnerable code not present
Red Hat CSAF VEX © Red Hat, Inc., from https://security.access.redhat.com/data/csaf/v2/vex/; changed: reduced to product statuses and remediations. CC BY 4.0 · csaf
CISA SSVC
- Exploitation
- Proof of concept is public
- Automatable
- no
- Technical impact
- total
- Assessed
- 7 mo ago
Exploit prediction
0.50% chance of exploitation in the next 30 days, higher than 42% of all scored CVEs (FIRST EPSS, 2026-11-08).
Exploits and checks
- github.com https://github.com/ggml-org/llama.cpp/security/advisories/GHSA-96jg-mvhq-q7q7 referenced PoC, tagged "exploit" by a source, unverified
CVSS scores
| assigned by | version | score | vector |
|---|---|---|---|
| CNA | 3.1 | 7.8 | CVSS:3.1/AV:L/AC:L/PR:N/UI:R/S:U/C:H/I:H/A:H |
Affected products
- ggml-org llama.cpp
Classification
References
-
github.com
/ggml-org/llama.cpp/security/advisories/GHSA-96jg-mvhq-q7q7
exploit, vendor-advisory
-
github.com
/ggml-org/llama.cpp/releases/tag/b7824
release-notes
Sources
- CVE List CVE-2026-33298
- NVD CVE-2026-33298
Fencer Vulns keeps one entry per vulnerability: the CVE id wins, then GHSA, and records that alias each other are merged, except that two CVEs always keep separate entries. The same data is available as JSON.