CVE-2026-18581: ggml-org llama.cpp · Reachable Assertion
Affects ggml-org llama.cppSource CVE Database V5
Public exploit available · CVSS 4.8 Medium.
Data as of 31 Oct 2026, 20:20 UTC
- EPSS
- 0.1% chance of exploitation in 30 days – higher than 5% of CVEsExploit Prediction Scoring System: the likelihood attackers will use this flaw soon.
CVSS:4.0/AV:L/AC:L/AT:N/PR:L/UI:N/VC:N/VI:N/VA:L/SC:N/SI:N/SA:N/E:PExploitation evidence
Disclosed: evidence found.
CVE published 3 Aug 2026
Detectable: no evidence on record.
No public nuclei template indexed
Weaponized: evidence found.
CVSS exploit maturity: proof of concept public
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), CVSS vector, the Metasploit, Exploit-DB and nuclei-templates index as of 31 Oct 2026.
What to do
Affected software
| Product | Affected | Fixed in |
|---|---|---|
| ggml-orgllama.cpp | Affected
| Fixed in– |
CPE configurations (1)
cpe:2.3:a:ggml-org:llama.cpp:*:*:*:*:*:*:*:*
AI-suggested
Since the vendor has not responded or provided a fix, users should restrict local access to trusted users and monitor for any updates from the vendor.
Description
CVE-2026-18581 is a medium severity vulnerability in the ggml-org llama.cpp project affecting the Jinja Minja Template Parser component. A reachable assertion can be triggered by manipulating input with the string {{9|9|{, requiring local access to exploit. The vulnerability has been publicly disclosed, but no official response or patch has been provided by the vendor yet.
References
- vuldb.com/vuln/385409 (opens in a new tab)
- vuldb.com/vuln/385409/cti (opens in a new tab)
- vuldb.com/cve/CVE-2026-18581 (opens in a new tab)
- vuldb.com/submit/799118 (opens in a new tab)
- github.com/ggml-org/llama.cpp/issues/25282 (opens in a new tab)
- drive.proton.me/urls/R8D8NGZ6Z0 (opens in a new tab)
- github.com/ggml-org/llama.cpp/ (opens in a new tab)