llama.cpp is an inference of several LLM models in C/C++. Prior to version b8492, the RPC backend's deserialize_tensor() skips all bounds validation when a tensor's buffer field is 0. An unauthenticated attacker can read and write arbitrary process memory via crafted GRAPH_COMPUTE messages.
Combined with pointer leaks from ALLOC_BUFFER/BUFFER_GET_BASE, this gives full ASLR bypass and remote code execution. No authentication required, just TCP access to the RPC server port. This issue has been patched in version b8492.
Attack Parameters
Attack Vector
Network
Can be exploited remotely
Attack Complexity
Low
Easy to exploit
Privileges Required
None
No privileges needed
User Interaction
None
No user interaction needed
Impact Assessment
Confidentiality
High
Complete data leak
Integrity
High
Complete data modification
Availability
High
Complete denial of service
CVSS Vector v3.1
Weakness Type (CWE)
References 3
https://github.com/ggml-org/llama.cpp/commit/39bf0d3c6a95803e0f41aaba069ffbee26…
security-advisories@github.com
https://github.com/ggml-org/llama.cpp/pull/20908
security-advisories@github.com
https://github.com/ggml-org/llama.cpp/security/advisories/GHSA-j8rj-fmpv-wcxw
security-advisories@github.com