Description (CNA)
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.
Affected (CNA)
| Vendor / product | Versions |
|---|---|
| ggml-org / llama.cpp | affected < b8492 |
CWE
CWE-119
References
- https://github.com/ggml-org/llama.cpp/security/advisories/GHSA-j8rj-fmpv-wcxw
- https://github.com/ggml-org/llama.cpp/pull/20908
- https://github.com/ggml-org/llama.cpp/commit/39bf0d3c6a95803e0f41aaba069ffbee26721042
ADP enrichment
No English description supplied.
No references supplied.