A security vulnerability has been detected in ggml-org llama.cpp 0.7.0-dev.
CVE-2026-134540
A security vulnerability has been detected in ggml-org llama.cpp 0.7.0-dev. This affects the function commonsamplerinit of the file common/sampling.cpp of the component llama-server. Such manipulation of the argument grammartriggers[].type leads to improper input validation. It is possible to launch the attack remotely. The exploit has been disclosed publicly and may be used. Upgrading to version b12405 mitigates this issue. The name of the patch is 9f26fe11c73c7e74a5e99e7f1b6370ad8e1cb22d. It is advisable to upgrade the affected component.
Part of the AI stack
This affects llama.cpp, in Inference & serving.
Assessment
- CVSS
- 6.9 (v4.0)
- Severity
- Medium
- Known exploited
- Not listed in CISA KEV
- Exploit availability
- Nothing found in Exploit-DB, Metasploit, Nuclei or public PoC repositories
- Published
- 21 November 2026
- Last updated
- 21 November 2026
- Assigner
- VulDB
CVSS vectorCVSS:4.0/AV:N/AC:L/AT:N/PR:N/UI:N/VC:N/VI:N/VA:L/SC:N/SI:N/SA:N/E:P
At the source
References
- https://vuldb.com/vuln/441681
- https://vuldb.com/vuln/441681/cti
- https://vuldb.com/cve/CVE-2026-134540
- https://vuldb.com/submit/1052496
- https://github.com/ggml-org/llama.cpp/issues/30835
- https://github.com/ggml-org/llama.cpp/pull/31478
- https://gist.github.com/Yunzez/90b17f91d7f1955805e0045a1a76fb6d#file-repro_llamacpp_grammar_triggers_abort-py
- https://github.com/ggml-org/llama.cpp/commit/9f26fe11c73c7e74a5e99e7f1b6370ad8e1cb22d
- https://github.com/ggml-org/llama.cpp/releases/tag/b12405
- https://github.com/ggml-org/llama.cpp/
Community proofs of concept
No community proof of concept yet. If you have one for a published vulnerability and the right to share it, add it below — it will appear here once reviewed.
Submit a proof of concept
Only for publicly disclosed vulnerabilities, and only material from testing you were authorised to perform. This platform does not buy, sell, or broker exploits — see earning from vulnerability research for legitimate bounty programs. Submissions are reviewed before they appear. Text only; do not include live credentials, personal data, or anything targeting systems you are not permitted to test.
Query this programmatically
Agents can read this through the MCP endpoint, or over HTTP:
curl https://cve.zerocrew.in/api/cve/CVE-2026-134540