CVE-2025-52566
llama.cpp tokenizer signed vs. unsigned heap overflow
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 Vector Breakdown
AV:LAttack VectorAC:LAttack ComplexityPR:NPrivileges RequiredUI:RUser InteractionS:CScopeC:HConfidentialityI:HIntegrityA:HAvailabilityWeaknesses
Affected Products
Exploitability
Exploit details including PoC links, Metasploit modules, and scanner templates are available after registration.
View exploit detailsAttack Graph
Click technique nodes for MITRE ATT&CK details · drag to pan · Ctrl/⌘ + scroll to zoom, or go fullscreen.
MITRE ATT&CK
2 techniquesReferences
Unlock Complete Vulnerability Intelligence
Get the full picture for CVE-2025-52566 and every CVE in our database. Create a free account — no credit card required.
Create Free Account