CVE-2026-133710
High 8.5No known exploitationFix status unknownTitle not yet published
Record last updated
CVSS score
8.5
High on a 0 to 10 scale
EPSS, chance of exploitation in 30 days
None
No EPSS score available
CISA remediation deadline
None
Not in the KEV catalog
Description
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.
Weakness: CWE-190
Patching and mitigation
- Patch status
- Unknown: no source documents a fix
- Mitigation
- None documented
- Vendor guidance
- No vendor link on record
Affected products
No affected products documented yet.
Timeline
- No dated events documented yet.
Vendor guidance and references
- https://github.com/ggml-org/llama.cpp/blob/b12555/src/models/hrm-text.cpp (opens in a new tab)
- https://github.com/ggml-org/llama.cpp/commit/50518b64c6f2191a116d2760042f106c4b3387d7 (opens in a new tab)
- https://github.com/ggml-org/llama.cpp/pull/32601 (opens in a new tab)
- https://github.com/ggml-org/llama.cpp/releases/tag/b12556 (opens in a new tab)
- https://www.vulncheck.com/advisories/llama-cpp-b11003-before-b12556-heap-out-of-bounds-write-via-hrm-text-model-loader (opens in a new tab)