CVE-2026-34159
Ggml Llama.cpp remote code execution
- Published1 Apr 2026
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 3.1 breakdown
CVSS:3.1/AV:N/AC:L/PR:N/UI:N/S:U/C:H/I:H/A:HAffected products
Remediation
References
Related CVEs
Recent high-severity vulnerabilities sharing a weakness type.
Frequently asked
Is CVE-2026-34159 being actively exploited?
CVE-2026-34159 is not in the CISA KEV catalog. A public exploit reference exists, so treat it as exploitable. Its EPSS exploit probability is 1.24%.
How severe is CVE-2026-34159?
CVE-2026-34159 has a CVSS 3.1 base score of 9.8, rated critical. EPSS estimates a 1.24% probability of exploitation.
Which products are affected by CVE-2026-34159?
Affected products include Ggml Llama.cpp.
How do I fix CVE-2026-34159?
Upgrade affected software to a fixed version, for example Ggml Llama.cpp b8492 or later, then confirm no affected versions remain in your inventory.
How Secuno handles this
Secuno correlates vulnerabilities like CVE-2026-34159 against the real software inventory on every managed device, as each hourly inventory arrives. Rather than a static severity, each match is scored in context: exploit availability, EPSS, the asset's exposure, and business criticality decide where it lands in the queue. If an affected version is present anywhere across your portfolio, it surfaces automatically with a prioritised remediation path.
Data from the NVD, CISA KEV catalog and FIRST EPSS. CVSS 3.1 base score shown where available.