llama.cpp b5854 before b11275 contains an integer overflow vulnerability in gguf_init_from_reader that bypasses the
Affects llama.cppSource GCVE Database
Mentioned vulnerabilities
Not known to be exploited · CVSS 6.9 Medium.
Data as of 28 Oct 2026, 22:33 UTC
CVSS:4.0/AV:L/AC:L/AT:N/PR:N/UI:P/VC:L/VI:N/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
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, avoid processing untrusted GGUF files or apply any vendor-recommended mitigations once published.
Description
An integer overflow vulnerability exists in llama.cpp versions before b11275 in the function gguf_init_from_reader. This flaw bypasses a prior size check (CVE-2025-53630) when handling tensor sizes near the maximum size limit. Attackers can craft a GGUF file with a tensor size that pads to zero, leading to an undersized data blob and out-of-bounds reads by consumers. The vulnerability has a CVSS score of 6.1, indicating medium severity.
References
- ubuntu.com/security/CVE-2026-116840 (opens in a new tab)
- cve.org/CVERecord?id=CVE-2026-116840 (opens in a new tab)
- github.com/cveproject/cvelistv5/tree/main/cves/2026/116xxx/cve-2026-116840.json (opens in a new tab)
- github.com/ggml-org/llama.cpp/blob/v0.5.0/ggml/src/gguf.cpp (opens in a new tab)
- github.com/ggml-org/llama.cpp/commit/a6ea155d3d38b3f6f43d0c0dc29c2d592413ef44 (opens in a new tab)
- github.com/ggml-org/llama.cpp/issues/26978 (opens in a new tab)
- github.com/ggml-org/llama.cpp/pull/26979 (opens in a new tab)
- github.com/ggml-org/llama.cpp/releases/tag/b11275 (opens in a new tab)
- nvd.nist.gov/vuln/detail/cve-2026-116840 (opens in a new tab)
- vulncheck.com/advisories/llama-cpp-b5854-before-b11275-integer-overflow-in-gguf-init-from-reader (opens in a new tab)