CVE-2026-34159
Last modified
CVE-2026-34159 is a critical-severity vulnerability rated 9.8/10 on the CVSS scale. 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. EPSS estimates a 1.13% chance of exploitation in the next 30 days.
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.
Metrics
CVSS:3.1/AV:N/AC:L/PR:N/UI:N/S:U/C:H/I:H/A:H
Weakness Enumeration
Affected Software
| Vendor | Product | Versions |
|---|---|---|
| Ggml | Llama.Cpp | < b8492 |
References
Timeline
- Published
- Last Modified
- Status
- Analyzed
Frequently Asked Questions
What is CVE-2026-34159?
How severe is CVE-2026-34159?
How do I fix CVE-2026-34159?
Are you affected by CVE-2026-34159?
Run a free Strix scan to check your systems for this vulnerability.
Scan your code nowSource: NVD / NIST
