google-veo
Pass
Audited by Gen Agent Trust Hub on Mar 12, 2026
Risk Level: SAFE
Full Analysis
- [EXTERNAL_DOWNLOADS]: The skill references the
infshCLI and provides installation instructions vianpx skills add inference-sh/skills@agent-tools. These resources belong to the vendor 'inference-sh' and are consistent with the skill's stated purpose of providing an interface to their platform. - [COMMAND_EXECUTION]: The skill uses the
infshcommand-line tool (infsh app run,infsh login,infsh app list) to interact with the Google Veo models. These are standard operations for the platform's CLI and do not involve unauthorized privilege escalation or dangerous system modifications. - [REMOTE_CODE_EXECUTION]: No patterns for arbitrary remote code execution were detected. The skill uses structured CLI commands to send prompts to a remote inference service.
Audit Metadata