llama.cpp: Unauthenticated RCE via GRAPH_COMPUTE buffer=0 bypass in llama.cpp RPC backend (ggml-org llama.cpp)
At a glance
- Source
- NVD
- EPSS
- EPSS 1.62 % · percentile 76 ()
- State
- PUBLISHED
- Published
- Updated
- Assigner
- GitHub_M
- NVD status
- Analyzed
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.
Weaknesses (CWE)
- CWE-119 — Improper Restriction of Operations within the Bounds of a Memory Buffer
References
Scores
| Version | Score | Vector | Scored by |
|---|---|---|---|
| CVSS 3.1 | CRITICAL 9.8 | CVSS:3.1/AV:N/AC:L/PR:N/UI:N/S:U/C:H/I:H/A:H | GitHub_M |
| CVSS 3.1 | CRITICAL 9.8 | CVSS:3.1/AV:N/AC:L/PR:N/UI:N/S:U/C:H/I:H/A:H | NVD · security-advisories@github.com (Secondary) |
European references
- ENISA EUVD · EUVD-2026-17975
- GCVE · GCVE-0-2026-34159
Affected configurations (NVD CPE)
cpe:2.3:a:ggml:llama.cpp:*:*:*:*:*:*:*:*< b8492
Affected products
| Product | Versions |
|---|---|
| ggml-org · llama.cpp | affected < b8492 |
Sources
| Source | Licence |
|---|---|
| CVE List (CVEProject cvelistV5) | CVE Program Terms of Use |
| EPSS (FIRST.org) | FIRST — attribution requested |
| ENISA EUVD | ENISA — reproduction authorised, source acknowledged |
| NVD (NIST) via fkie-cad/nvd-json-data-feeds | Public domain — this product uses data from the NVD API but is not endorsed or certified by the NVD |