google-veo
Pass
Audited by Gen Agent Trust Hub on Mar 17, 2026
Risk Level: SAFE
Full Analysis
- [COMMAND_EXECUTION]: The skill utilizes the
infshcommand-line tool for authenticating users (infsh login), searching available models (infsh app list), and executing video generation tasks (infsh app run). These commands are standard operations for the vendor's platform. - [EXTERNAL_DOWNLOADS]: The documentation references the installation of additional agent skills using
npx skills add. These references point directly to the author's official repository (inference-sh/skills), which is a trusted source in the context of this skill. - [SAFE]: No evidence of prompt injection, data exfiltration, obfuscation, or unauthorized privilege escalation was found in the skill metadata or instructions.
Audit Metadata