llama.cpp before b3701 contains an out-of-bounds read vulnerability in llama_decode_internal and llama_encode_internal that allows remote unauthenticated attackers to read memory by supplying unvalidated token IDs. Attackers can send integer-array prompts to the llama-server /completion endpoint with IDs outside 0 to n_vocab to read embedding memory out of bounds or crash the process.
Attack Parameters
Attack Vector
Network
Can be exploited remotely
Attack Complexity
Low
Easy to exploit
Attack Requirements
None
No additional conditions
Privileges Required
None
No privileges needed
User Interaction
None
No user interaction needed
Impact Assessment
Confidentiality
Low
Partial 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/b3681/examples/server/server.cpp#L789
disclosure@vulncheck.com
https://github.com/ggml-org/llama.cpp/commit/eae597182cb61bbde0b26e7cec5999d28b…
disclosure@vulncheck.com
https://github.com/ggml-org/llama.cpp/commit/faf69d4237c9ae4d7f572b4674d1002463…
disclosure@vulncheck.com
https://github.com/ggml-org/llama.cpp/pull/9359
disclosure@vulncheck.com
https://github.com/ggml-org/llama.cpp/releases/tag/b3701
disclosure@vulncheck.com
https://www.vulncheck.com/advisories/llama-cpp-before-b3701-out-of-bounds-read-…
disclosure@vulncheck.com