Buffer overflow in Ggml-org Llama.cpp
CVE-2025-52566
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 unint…
Vulnerability class: Buffer Overflow
EPSS: 0.002 (45.7th percentile) — read the EPSS interpretation.
CVSS v3 metric
CVSS v3 base score 8.6 (High). Vector: CVSS:3.1/AV:L/AC:L/PR:N/UI:R/S:C/C:H/I:H/A:H.
Affected products
- Ggml-org Llama.cpp — versions < b5721
Weakness classification (CWE)
Public proof-of-concept exploits
References
- https://github.com/ggml-org/llama.cpp/security/advisories/GHSA-7rxv-5jhh-j6xx (x_refsource_CONFIRM)
- https://github.com/ggml-org/llama.cpp/commit/dd6e6d0b6a4bbe3ebfc931d1eb14db2f2b1d70af (x_refsource_MISC)
Frequently asked questions
- What is CVE-2025-52566?
- CVE-2025-52566 is a high-severity vulnerability in Ggml-org Llama.cpp, classified under Improper Restriction of Operations within the Bounds of a Memory Buffer. CVSS score: 8.6/10. Published 2025-06-24.
- How severe is CVE-2025-52566?
- High severity. CVSS v3 base score is 8.6 out of 10.
- Is CVE-2025-52566 known to be exploited?
- 1 public proof-of-concept repositories are indexed. Not currently listed in the CISA KEV catalog.