CVE-2025-52566

unknown

Published — · Modified —

💬 Discuss on Community ✚ Propose mitigation

CVSS v3

—

CVSS v4 NEW

—

not yet in upstream

VIR risk

—

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.

Predictions

Exploit likelihood

20%

Patch ETA

—

Heuristic predictions, AS-IS, for prioritization only.

Mitigations

No mitigations published for this CVE yet.

The vendor-content worker queues fetches as references arrive (check back in a few minutes). Or — if you've already worked around this in production — publish your fix to the community-verified tier.

✚ Propose a mitigation on Community → Mitigations published via the community go through AI scoring + 2 human reviewers + 7-day silent objection window before landing here with source_tier=community-verified.

OS impact

OS	Version	Status	Fixed in
sles		affected
debian	forky	fixed	`5760+dfsg-1`
debian	sid	fixed	`5760+dfsg-1`

References

Community-verified mitigations for this CVE will appear above when contributors publish them.

Verify integrity in audit chain (admin only). AS-IS.