CVE-2026-126976: (llama.cpp MTMD Multimodal GGUF File Parsing Integer Overflow Remote Co ...)
Affects llama.cppSource GCVE Database
Not known to be exploited · CVSS 7.0 High.
Data as of 19 Nov 2026, 03:22 UTC
Thin evidence
One scorer or none| CNA (zdi) | CVSS 3.0 | 7.0 |
|---|
CVSS:3.0/AV:L/AC:H/PR:N/UI:R/S:U/C:H/I:H/A:HExploitation evidence
Disclosed: evidence found.
CVE published 17 Nov 2026
Detectable: no evidence on record.
No public nuclei template indexed
Weaponized: 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 18 Nov 2026.
What to do
Affected software
| Product | Affected | Fixed in |
|---|---|---|
Ubuntu 26.10llama.cpppkg:deb/ubuntu/llama.cpp?arch=source&distro=stonkingOther threats | Affected
| Fixed in– |
Ubuntu 26.04 LTSllama.cpppkg:deb/ubuntu/llama.cpp?arch=source&distro=resoluteOther threats | Affected
| 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, limit local access to trusted users and avoid opening untrusted GGUF files with the affected versions of llama.cpp. Monitor official vendor channels for updates and patches.
Description
A high-severity integer overflow vulnerability exists in the GGUF file parsing component of llama.cpp's MTMD Multimodal feature. This flaw could potentially allow remote code execution under certain conditions. The vulnerability affects specific versions of llama.cpp as listed. The CVSS 3.0 score is 7.0, indicating a high impact on confidentiality, integrity, and availability. No known exploits are reported in the wild, and no patch information is provided in the available data.