CVE-2026-34159
Critical
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.
SeverityCritical
CVSS9.8
Exploit probability—
ProductGgml Llama.cpp
PublishedApr 1, 2026
First seenApr 1, 2026
Weakness typeCWE-119Memory buffer bounds error
How to fix
Update
- ggml llama.cppb8492 or later
Affected products
| Product | Affected versions | Fixed in |
|---|---|---|
| ggml llama.cpp | v < b8492 | b8492 |
Check your version
Choose the product and enter the version you run to see whether it falls in the affected range.
In the Intelligence 360 plan
Attack Surface Management
See the assets tied to your domains, the technologies they run and known vulnerabilities in one list.