DEBIAN-CVE-2026-33298
- Source
- https://security-tracker.debian.org/tracker/CVE-2026-33298
- Import Source
- https://storage.googleapis.com/debian-osv/debian-cve-osv/DEBIAN-CVE-2026-33298.json
- JSON Data
- https://api.osv.dev/v1/vulns/DEBIAN-CVE-2026-33298
- Upstream
- Published
- 2026-03-24T01:17:01Z
- Modified
- 2026-09-14T17:03:29Z
- Severity
-
- 7.8 (High) CVSS_V3 - CVSS:3.1/AV:L/AC:L/PR:N/UI:R/S:U/C:H/I:H/A:H CVSS Calculator
- Summary
- [none]
- Details
-
llama.cpp is an inference of several LLM models in C/C++. Prior to b7824, an integer overflow vulnerability in the
ggml_nbytesfunction allows an attacker to bypass memory validation by crafting a GGUF file with specific tensor dimensions. This causesggml_nbytesto 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. - References
Affected packages
Debian:14 / llama.cpp
Package
- Name
- llama.cpp
- Purl
- pkg:deb/debian/llama.cpp?arch=source&distro=forky
Affected ranges
- Type
- ECOSYSTEM
- Events
-
Introduced0 Unknown introduced version / All previous versions are affectedFixed7965+dfsg-1
Affected versions
Other
5151+dfsg-1~exp2
5151+dfsg-1~exp3
5318+dfsg-1
5318+dfsg-2
5713+dfsg-1
5760+dfsg-1
5760+dfsg-2
5760+dfsg-3
5760+dfsg-4
5882+dfsg-1
5882+dfsg-2
5882+dfsg-3~exp1
5882+dfsg-3~exp2
5882+dfsg-3~exp3
5882+dfsg-3
5882+dfsg-4
6641+dfsg-1
6641+dfsg-2
6641+dfsg-3
7593+dfsg-1
7593+dfsg-2
7593+dfsg-3