Bug 2374503 (CVE-2025-52566)

Summary: CVE-2025-52566 llama-cpp: llama.cpp heap overflow
Product: [Other] Security Response Reporter: OSIDB Bzimport <bzimport>
Component: vulnerabilityAssignee: Product Security DevOps Team <prodsec-dev>
Status: NEW --- QA Contact:
Severity: high Docs Contact:
Priority: high    
Version: unspecifiedKeywords: Security
Target Milestone: ---   
Target Release: ---   
Hardware: All   
OS: Linux   
Whiteboard:
Fixed In Version: Doc Type: ---
Doc Text:
A flaw was found in the tokenizer component of llama.cpp. This vulnerability allows heap memory corruption via carefully crafted text input during tokenization, due to a signed vs. unsigned integer overflow in the llama_vocab::tokenize function.
 Story Points: ---
Clone Of: Environment:
Last Closed: Type: ---
Regression: --- Mount Type: ---
Documentation: --- CRM:
Verified Versions: Category: ---
oVirt Team: --- RHEL 7.3 requirements from Atomic Host:
Cloudforms Team: --- Target Upstream Version:
Embargoed:
Bug Depends On: 2374627, 2374628    
Bug Blocks:    

Description OSIDB Bzimport 2025-06-24 04:01:35 UTC 
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.