Out-of-Bounds Affecting llama.cpp package, versions <8611+dfsg-1
Threat Intelligence
Snyk has a proof-of-concept or detailed explanation of how to exploit this vulnerability.
The probability is the direct output of the EPSS model, and conveys an overall sense of the threat of exploitation in the wild. The percentile measures the EPSS probability relative to all known EPSS scores. Note: This data is updated daily, relying on the latest available EPSS model version. Check out the EPSS documentation for more details.
Do your applications use this vulnerable package?
In a few clicks we can analyze your entire application and see what components are vulnerable in your application, and suggest you quick fixes.
Test your applications- Snyk IDSNYK-DEBIAN14-LLAMACPP-16066081
- published15 Apr 2026
- disclosed1 Apr 2026
Introduced: 1 Apr 2026
CVE-2026-34159 (opens in a new tab)How to fix?
Upgrade Debian:14 llama.cpp to version 8611+dfsg-1 or higher.
NVD Description
Note: Versions mentioned in the description apply only to the upstream llama.cpp package and not the llama.cpp package as distributed by Debian.
See How to fix? for Debian:14 relevant fixed versions and status.
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.
References
- https://security-tracker.debian.org/tracker/CVE-2026-34159
- 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
- https://github.com/casp3r0x0/CVE-2026-34159