CVE-2026-116816: ggml-org llama.cpp · Improper Validation of Array Index
Affects ggml-org llama.cppSource CVE Database V5
Not known to be exploited · CVSS 8.5 High : upgrade to b10261 soon.
Data as of 27 Oct 2026, 01:12 UTC
- Patch
- Available – fixed in b10261
CVSS:4.0/AV:L/AC:L/AT:N/PR:N/UI:P/VC:H/VI:H/VA:H/SC:N/SI:N/SA:NExploitation evidence
Disclosed: evidence found.
CVE published 27 Oct 2026
Detectable: no evidence on record.
No public nuclei template indexed
Weaponised: no evidence on record.
No public exploit code indexed in Metasploit or Exploit-DB
Exploited in the wildExploited: no evidence on record.
Not in CISA KEV and no source reports exploitation
Observed by OffSeq MirageSeen by Mirage: no evidence on record.
No attack traffic recorded by OffSeq Mirage sensors
A missing step is not evidence of safety. Sources: cve.org (opens in a new tab), the Metasploit, Exploit-DB and nuclei-templates index as of 26 Oct 2026.
What to do
Upgrade ggml-org llama.cpp to b10261.
Affected software
| Product | Affected | Fixed in |
|---|---|---|
| ggml-orgllama.cpp | Affected
| Fixed in
|
GitHubllama.cpppkg:github/llama.cppOther threats | Affected
| Fixed in– |
Check your own hosts for these packages with threat-finder (opens in a new tab), our free open-source scanner.
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.
References
- github.com/ggml-org/llama.cpp/pull/25969 (opens in a new tab)
- github.com/ggml-org/llama.cpp/pull/26511 (opens in a new tab)
- github.com/ggml-org/llama.cpp/commit/cf06ad7dfe79e7bf2934150d4fefe1ce8db05490 (opens in a new tab)
- github.com/ggml-org/llama.cpp/blob/b10259/src/llama-vocab.cpp (opens in a new tab)
- github.com/ggml-org/llama.cpp/releases/tag/b10261 (opens in a new tab)
- vulncheck.com/advisories/llama-cpp-b5899-before-b10261-heap-out-of-bounds-write-via-plamo2-tokenizer (opens in a new tab)