CVE-2025-52566
Publication date 24 June 2025
Last updated 24 June 2025
Ubuntu priority
llama.cpp is an inference of several LLM models in C/C++. Prior to version b5721, there is a signed vs. unsigned integer overflow in llama.cpp's tokenizer implementation (llama_vocab::tokenize) (src/llama-vocab.cpp:3036) resulting in unintended behavior in tokens copying size comparison. Allowing heap-overflowing llama.cpp inferencing engine with carefully manipulated text input during tokenization process. This issue has been patched in version b5721.
Status
| Package | Ubuntu Release | Status |
|---|---|---|
| llama.cpp | 25.04 plucky | Not in release |
| 24.10 oracular | Not in release | |
| 24.04 LTS noble | Not in release | |
| 22.04 LTS jammy | Not in release |
Severity score breakdown
| Parameter | Value |
|---|---|
| Base score |
8.6 · High
|
| Attack vector | Local |
| Attack complexity | Low |
| Privileges required | None |
| User interaction | Required |
| Scope | Changed |
| Confidentiality | High |
| Integrity impact | High |
| Availability impact | High |
| Vector | CVSS:3.1/AV:L/AC:L/PR:N/UI:R/S:C/C:H/I:H/A:H |
References
Other references
- https://www.cve.org/CVERecord?id=CVE-2025-52566
- https://github.com/ggml-org/llama.cpp/security/advisories/GHSA-7rxv-5jhh-j6xx
- https://github.com/ggml-org/llama.cpp/commit/dd6e6d0b6a4bbe3ebfc931d1eb14db2f2b1d70af (b5721)
- https://github.com/ggml-org/llama.cpp/commit/dd6e6d0b6a4bbe3ebfc931d1eb14db2f2b1d70af