CVE-2026-116816
7.8 HIGHpublic exploit availablePublished 2026-10-27 · Updated 2026-10-27
AI analysis for this CVE has not been generated yet. Raw NVD data is shown below.
NVD 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 vector
CVSS:3.1/AV:L/AC:L/PR:N/UI:R/S:U/C:H/I:H/A:H
Weaknesses
CWE-129
Public exploit & PoC references
- https://github.com/ggml-org/llama.cpp/blob/b10259/src/llama-vocab.cpp#L1376-L1377
- https://github.com/ggml-org/llama.cpp/commit/cf06ad7dfe79e7bf2934150d4fefe1ce8db05490
- 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
All references
- https://github.com/ggml-org/llama.cpp/blob/b10259/src/llama-vocab.cpp#L1376-L1377
- https://github.com/ggml-org/llama.cpp/commit/cf06ad7dfe79e7bf2934150d4fefe1ce8db05490
- 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-bounds-write-via-plamo2-tokenizer
Source data: NVD (nvd.nist.gov), public domain. Exploit-DB.ai adds local AI analysis for defensive use only.
Related CVEs
- HIGHCVE-2024-58400PoC
- MEDIUMCVE-2026-100654PoC
- MEDIUMCVE-2026-100836PoC
- UNSCOREDCVE-2026-102510
- UNSCOREDCVE-2026-102511
- LOWCVE-2026-102822PoC
- MEDIUMCVE-2026-103220
- HIGHCVE-2026-103672PoC
Related by shared AI tags and CWE weakness class. Browse the full archive.