CVE-2026-133710
llama.cpp b11003 before b12556 contains an integer overflow in the hrm_text loader load_arch_hparams() that allows attackers to bypass the block count check us…
Impact
llama.cpp b11003 before b12556 contains an integer overflow in the hrm_text loader load_arch_hparams() that allows attackers to bypass the block count check using crafted GGUF metadata. Attackers can supply a GGUF model whose layer factors wrap modulo 2^32, causing load_arch_tensors() to write tensor pointers past model.layers, corrupting heap memory and potentially enabling code execution.
An attacker can exploit this with local access to the system, without logging in, but a user has to be involved, for example by viewing content. If it succeeds: high risk of data being read, high risk of data or systems being changed, high risk of outages.
Affected products · Ggml-org
| Product | Affected versions |
|---|---|
| Llama.cpp | from b11003 before b12556 |
Weakness classification
References
- NVD record
- CVE.org record
- GitHub advisory
- https://github.com/ggml-org/llama.cpp/pull/32601
- https://github.com/ggml-org/llama.cpp/commit/50518b64c6f2191a116d2760042f106c4b3387d7
- https://github.com/ggml-org/llama.cpp/blob/b12555/src/models/hrm-text.cpp
- https://github.com/ggml-org/llama.cpp/releases/tag/b12556
- https://www.vulncheck.com/advisories/llama-cpp-b11003-before-b12556-heap-out-of-bounds-write-via-hrm-text-model-loader
- https://github.com/advisories/GHSA-92hv-w2fh-9w89
- https://nvd.nist.gov/vuln/detail/CVE-2026-133710