CVE-2025-52566
HIGH EPSS 23.6%
Published Jun 24, 20251y ago · Modified Jun 17, 20262w ago
8.8 CVSS 3.1
Published Jun 24, 2025 1y ago
Last Modified Jun 17, 2026 2w ago
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.
CVSS Details
Base Score
Exploitability
Impact
Vector string
CVSS:3.1/AV:N/AC:L/PR:N/UI:R/S:U/C:H/I:H/A:H Attack Vector Network
Attack Complexity Low
Privileges Required None
User Interaction Required
Scope Unchanged
Confidentiality High
Integrity High
Availability High
Threat Intelligence
EPSS Exploit Probability
23.6% percentile
Exploit & Patch Status
Public Exploit Known
Patch Available
Weaknesses 2
CWE-119 Improper Restriction of Operations within the Bounds of a Memory Buffer Memory Safety
CWE-195
Affected Products 1
| Vendor | Product | Version | Range |
|---|---|---|---|
| ggml | llama.cpp | * | <b5721 |
References 2
- github.com https://github.com/ggml-org/llama.cpp/commit/dd6e6d0b6a4bbe3ebfc931d1eb14db2f2b1d70af
- github.com https://github.com/ggml-org/llama.cpp/security/advisories/GHSA-7rxv-5jhh-j6xx
Remediation
- github.com https://github.com/ggml-org/llama.cpp/commit/dd6e6d0b6a4bbe3ebfc931d1eb14db2f2b1d70af