CVE-2025-52566
Last modified
CVE-2025-52566 is a high-severity vulnerability rated 8.8/10 on the CVSS scale. llama.cpp is an inference of several LLM models in C/C++. Prior to version b5721, there is a signed vs. EPSS estimates a 0.32% chance of exploitation in the next 30 days.
Description
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.
Metrics
CVSS:3.1/AV:N/AC:L/PR:N/UI:R/S:U/C:H/I:H/A:H
Weakness Enumeration
Affected Software
| Vendor | Product | Versions |
|---|---|---|
| Ggml | Llama.Cpp | < b5721 |
References
Timeline
- Published
- Last Modified
- Status
- Analyzed
Frequently Asked Questions
What is CVE-2025-52566?
How severe is CVE-2025-52566?
How do I fix CVE-2025-52566?
Are you affected by CVE-2025-52566?
Run a free Strix scan to check your systems for this vulnerability.
Scan your code nowSource: NVD / NIST
