CVSS: 8.6EPSS: 0%CPEs: 1EXPL: 0CVE-2025-52566 – llama.cpp tokenizer signed vs. unsigned heap overflow
https://notcve.org/view.php?id=CVE-2025-52566
24 Jun 2025 — 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. • https://github.com/ggml-org/llama.cpp/commit/dd6e6d0b6a4bbe3ebfc931d1eb14db2f2b1d70af • CWE-119: Improper Restriction of Operations within the Bounds of a Memory Buffer CWE-195: Signed to Unsigned Conversion Error •
CVSS: 10.0EPSS: 0%CPEs: 1EXPL: 0CVE-2025-49847 – llama.cpp Vulnerable to Buffer Overflow via Malicious GGUF Model
https://notcve.org/view.php?id=CVE-2025-49847
17 Jun 2025 — llama.cpp is an inference of several LLM models in C/C++. Prior to version b5662, an attacker‐supplied GGUF model vocabulary can trigger a buffer overflow in llama.cpp’s vocabulary‐loading code. Specifically, the helper _try_copy in llama.cpp/src/vocab.cpp: llama_vocab::impl::token_to_piece() casts a very large size_t token length into an int32_t, causing the length check (if (length < (int32_t)size)) to be bypassed. As a result, memcpy is still called with that oversized size, letting a malicious model ove... • https://github.com/ggml-org/llama.cpp/commit/3cfbbdb44e08fd19429fed6cc85b982a91f0efd5 • CWE-119: Improper Restriction of Operations within the Bounds of a Memory Buffer CWE-195: Signed to Unsigned Conversion Error •