google-veo
Pass
Audited by Gen Agent Trust Hub on Jun 12, 2026
Risk Level: SAFE
Full Analysis
- [EXTERNAL_DOWNLOADS]: The skill provides instructions to install the
beltCLI and related skills from theinference-shandbelt-shorganizations via NPM and GitHub. These references point to the official infrastructure of the service provider used by the skill. - [COMMAND_EXECUTION]: The skill utilizes the
Bashtool to executebeltCLI commands for authentication, searching the model store, and triggering video generation. Theallowed-toolsconfiguration in the frontmatter restricts the agent's shell access specifically to thebeltcommand, implementing a least-privilege security posture. - [DATA_EXFILTRATION]: No unauthorized data access or transmission patterns were identified. The
belt logincommand is part of the standard authentication process for the third-party service.
Audit Metadata