Buffer overflow in Ggml Llama.cpp
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.
Vulnerability class: Buffer Overflow
Published · last modified .
CVSS v3 metric
CVSS v3 base score 9.8 (Critical). Vector: CVSS:3.1/AV:N/AC:L/PR:N/UI:N/S:U/C:H/I:H/A:H.
EPSS exploit prediction
EPSS: 0.012 (68.0th percentile), scored .
Low probability of exploitation in the next 30 days, but still tracked. 68th percentile — 68.0% of CVEs in the catalogue have a lower EPSS than this one. How to read EPSS.
EPSS over last 30 days · oldest: 0.011 · newest: 0.012 · change: +0.001
Affected products
- Ggml Llama.cpp
- Ggml-Org Llama.cpp — versions < b8492
Weakness classification (CWE)
Public proof-of-concept exploits
References
- github.com/ggml-org/llama.cpp/security/advisories/GHSA-j8rj-fmpv-wcxw (Exploit, Vendor Advisory)
- github.com/ggml-org/llama.cpp/pull/20908 (Patch, Issue Tracking)
- github.com/ggml-org/llama.cpp/commit/39bf0d3c6a95803e0f41aaba069ffbee26721042 (Patch)
Frequently asked questions
- What is CVE-2026-34159?
- CVE-2026-34159 is a critical-severity vulnerability in Ggml Llama.cpp, classified under Improper Restriction of Operations within the Bounds of a Memory Buffer. CVSS score: 9.8/10. Published 2026-04-01.
- How severe is CVE-2026-34159?
- Critical severity. CVSS v3 base score is 9.8 out of 10.
- Is CVE-2026-34159 known to be exploited?
- 3 public proof-of-concept repositories are indexed. Not currently listed in the CISA KEV catalog.