CVE-2026-34159

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 3.1

9.8CVSS:3.1/AV:N/AC:L/PR:N/UI:N/S:U/C:H/I:H/A:H

EPSS

1.6% chance of exploitation in the next 30 days; higher than 75% of CVEs (scores of 2026-10-26)

CWE

CWE-119

Published

2026-04-01

Modified

2026-10-26

Record from

the NVD, synced 2026-10-26

Affected

• ggml:llama.cpp

References

• https://github.com/ggml-org/llama.cpp/commit/39bf0d3c6a95803e0f41aaba069ffbee26721042
• https://github.com/ggml-org/llama.cpp/pull/20908
• https://github.com/ggml-org/llama.cpp/security/advisories/GHSA-j8rj-fmpv-wcxw

Check your stackJSON