llama.cpp before b5649 contains a heap out-of-bounds read vulnerability in llama_vocab::impl::print_info() that allows attackers to crash model loading via oversized special token IDs. Attackers can supply a crafted GGUF model with a short tokenizer.ggml.tokens array, causing llama-cli or llama-server to read past id_to_token and crash.
Attack Parameters
Attack Vector
Local
Requires local access
Attack Complexity
Low
Easy to exploit
Attack Requirements
None
No additional conditions
Privileges Required
None
No privileges needed
User Interaction
Passive
Minimal interaction
Impact Assessment
Confidentiality
None
No data leak
Integrity
None
No data modification
Availability
High
Complete denial of service
CVSS Vector v4.0
Weakness Type (CWE)
References 6
https://github.com/ggml-org/llama.cpp/blob/b5648/src/llama-vocab.cpp#L2771
disclosure@vulncheck.com
https://github.com/ggml-org/llama.cpp/commit/c33fe8b8c4427202706b1434e9fc8ab575…
disclosure@vulncheck.com
https://github.com/ggml-org/llama.cpp/pull/14145
disclosure@vulncheck.com
https://github.com/ggml-org/llama.cpp/releases/tag/b5649
disclosure@vulncheck.com
https://github.com/ggml-org/llama.cpp/security/advisories/GHSA-g4cc-763q-h9h6
disclosure@vulncheck.com
https://www.vulncheck.com/advisories/llama-cpp-before-b5649-heap-out-of-bounds-…
disclosure@vulncheck.com