Vulnerability Description
llama.cpp b5899 before b10261 contains a heap out-of-bounds write vulnerability in llm_tokenizer_plamo2::build that allows attackers to corrupt heap memory via crafted GGUF models. Attackers can supply BYTE-typed token text like <0x-1> whose negative parsed value writes token ids before the bytes_ buffer during model loading, causing crashes or potential code execution.
CVSS Score
HIGH
Related Weaknesses (CWE)
References
- https://github.com/ggml-org/llama.cpp/blob/b10259/src/llama-vocab.cpp#L1376-L137
- https://github.com/ggml-org/llama.cpp/commit/cf06ad7dfe79e7bf2934150d4fefe1ce8db
- https://github.com/ggml-org/llama.cpp/pull/25969
- https://github.com/ggml-org/llama.cpp/pull/26511
- https://github.com/ggml-org/llama.cpp/releases/tag/b10261
- https://www.vulncheck.com/advisories/llama-cpp-b5899-before-b10261-heap-out-of-b
FAQ
What is CVE-2026-116816?
CVE-2026-116816 is a vulnerability with a CVSS score of 7.8 (HIGH). llama.cpp b5899 before b10261 contains a heap out-of-bounds write vulnerability in llm_tokenizer_plamo2::build that allows attackers to corrupt heap memory via crafted GGUF models. Attackers can suppl...
How severe is CVE-2026-116816?
CVE-2026-116816 has been rated HIGH with a CVSS base score of 7.8/10. Review the CVSS metrics above for detailed severity breakdown.
Is there a patch for CVE-2026-116816?
Check the references section above for vendor advisories and patch information. Review vendor security bulletins for remediation guidance.