VulnerabilityAnalyzed

CVE-2025-52566

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.

HIGH 8.8EPSS 0.32%

Does this matter?

High impact if exploited, but EPSS currently rates exploitation as unlikely (0.32%). Schedule it in the normal patch cycle and watch for a rise in EPSS or a public exploit.

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 3.1: 8.8 HIGHCVSS:3.1/AV:N/AC:L/PR:N/UI:R/S:U/C:H/I:H/A:H
EPSS: 0.32% probability · 25th percentile
CISA KEV: Not listed
Weakness: CWE-119, CWE-195
Affected: ggml/llama.cpp
Source: security-advisories@github.com

References

https://github.com/ggml-org/llama.cpp/commit/dd6e6d0b6a4bbe3ebfc931d1eb14db2f2b1d70afPatch
https://github.com/ggml-org/llama.cpp/security/advisories/GHSA-7rxv-5jhh-j6xxExploit, Vendor Advisory
https://github.com/ggml-org/llama.cpp/security/advisories/GHSA-7rxv-5jhh-j6xxExploit, Vendor Advisory

Source: NVD record, EPSS from FIRST.org, KEV from CISA. Refreshed daily.