What’s Vulnerable › Vulnerabilities

CVE-2025-52566: llama.cpp tokenizer signed vs. unsigned heap overflow

• Severity: high (CVSS 8.8 v3.1)
• Exploited in the wild: not listed in CISA KEV
• EPSS: 0.4% probability of exploitation in the next 30 days
• Public exploit or detection template: yes
• Published: 2025-06-24 · updated 2026-06-17
• Weakness: CWE-119

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.

Affected products

• ggml-org llama.cpp: before b5721 — fixed in b5721

How to fix

Upgrade to a fixed version: ggml-org llama.cpp b5721. Check the vendor advisory for mitigations.

References

• https://github.com/ggml-org/llama.cpp/commit/dd6e6d0b6a4bbe3ebfc931d1eb14db2f2b1d70af
• https://github.com/ggml-org/llama.cpp/security/advisories/GHSA-7rxv-5jhh-j6xx
• https://github.com/ggml-org/llama.cpp/security/advisories/GHSA-7rxv-5jhh-j6xx

Get alerted when CVE-2025-52566 or the next vulnerability affects your stack