Vulnerability · Published Oct 27, 2026 · Assigned by VulnCheck

CVE-2026-116816llama.cpp b5899 before b10261 Heap Out-of-Bounds Write via plamo2 Tokenizer

High 7.8

In plain English

A high-severity security flaw in llama.cpp from ggml-org. There are no confirmed reports of exploitation so far. The chance it is exploited in the next 30 days is estimated at 0.1% (higher than 3% of all known vulnerabilities). Fixed versions are available - upgrade the affected package.

Severity (CVSS 3.1)7.8High

Exploit odds (30 days)0.1%top 97.0% of all CVEs

Exploited in the wildNo reportsCISA SSVC: none

Attack toolingNoneno public tooling known

Official 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.

Affected packages & fixed versions

Ecosystem	Package	Fixed in	Advisory
Debian:14	llama.cpp	10271+dfsg-1	DEBIAN-CVE-2026-116816
Ubuntu:26.04:LTS	llama.cpp	no fix listed	UBUNTU-CVE-2026-116816
Ubuntu:26.10	llama.cpp	no fix listed	UBUNTU-CVE-2026-116816

Affected products (as reported)

Vendor	Product	Versions
ggml-org	llama.cpp	b5899 – before b10261

Weakness: CWE-129 · Vector: CVSS:3.1/AV:L/AC:L/PR:N/UI:R/S:U/C:H/I:H/A:H

References

https://github.com/ggml-org/llama.cpp/pull/25969 issue-tracking, patch
https://github.com/ggml-org/llama.cpp/pull/26511 patch, issue-tracking
https://github.com/ggml-org/llama.cpp/commit/cf06ad7dfe79e7bf2934150d4fefe1ce8db05490 patch
https://github.com/ggml-org/llama.cpp/blob/b10259/src/llama-vocab.cpp#L1376-L1377 technical-description
llama.cpp b10261 Release Notes release-notes
VulnCheck Advisory: llama.cpp b5899 before b10261 Heap Out-of-Bounds Write via plamo2 Tokenizer third-party-advisory