Skip to main content
CVE-2026-116816VulnerabilityPublished Updated

llama.cpp b5899 before b10261 contains a heap out-of-bounds write vulnerability in llm_tokenizer_plamo2::build that

Affects llama.cppSource GCVE Database

0
Authoritative record:CVE-2026-116816· High 8.5

Not known to be exploited · CVSS 8.5 High.

Data as of 28 Oct 2026, 22:32 UTC

CVSS 4.0 base score
8.5High
How severe the flaw is on the 0–10 CVSS scale.
CVSS:4.0/AV:L/AC:L/AT:N/PR:N/UI:P/VC:H/VI:H/VA:H/SC:N/SI:N/SA:N

Exploitation evidence

  1. Disclosed: evidence found.

    CVE published 27 Oct 2026

  2. Detectable: no evidence on record.

    No public nuclei template indexed

  3. Weaponised: no evidence on record.

    No public exploit code indexed in Metasploit or Exploit-DB

  4. Exploited in the wild: no evidence on record.

    Not in CISA KEV and no source reports exploitation

  5. Observed by OffSeq 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

Affected software

ProductAffectedFixed in
Ubuntu 26.10llama.cpppkg:deb/ubuntu/llama.cpp?arch=source&distro=stonkingOther threatsAffected
  • 8681+dfsg-1 – 10438+dfsg-1ubuntu1
4 affected builds
Fixed in–
Ubuntu 26.04 LTSllama.cpppkg:deb/ubuntu/llama.cpp?arch=source&distro=resoluteOther threatsAffected
  • =5882+dfsg-2
  • =8064+dfsg-1ubuntu1
  • =8681+dfsg-1
Fixed in–

Check your own hosts for these packages with threat-finder (opens in a new tab), our free open-source scanner.

AI-suggested

Until a fix is available, avoid loading untrusted or crafted GGUF models to mitigate risk.

Description

A heap out-of-bounds write vulnerability exists in llama.cpp versions before b10261 in the llm_tokenizer_plamo2::build function. This flaw allows attackers to corrupt heap memory by supplying crafted GGUF models with specially crafted BYTE-typed token text containing negative parsed values. The vulnerability can cause crashes or potentially enable code execution during model loading.

References

Community reviews

Loading reviews…