Vulnerability Description
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.
CVSS Score
CRITICAL
Affected Products
| Vendor | Product | Versions |
|---|---|---|
| Ggml | Llama.Cpp | < b8492 |
Related Weaknesses (CWE)
References
- https://github.com/ggml-org/llama.cpp/commit/39bf0d3c6a95803e0f41aaba069ffbee267Patch
- https://github.com/ggml-org/llama.cpp/pull/20908Issue TrackingPatch
- https://github.com/ggml-org/llama.cpp/security/advisories/GHSA-j8rj-fmpv-wcxwExploitVendor Advisory
FAQ
What is CVE-2026-34159?
CVE-2026-34159 is a vulnerability with a CVSS score of 9.8 (CRITICAL). 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 unauthenticat...
How severe is CVE-2026-34159?
CVE-2026-34159 has been rated CRITICAL with a CVSS base score of 9.8/10. This is considered a critical vulnerability requiring immediate attention.
Is there a patch for CVE-2026-34159?
Check the references section above for vendor advisories and patch information. Affected products include: Ggml Llama.Cpp.