video-ad-specs
Pass
Audited by Gen Agent Trust Hub on Jul 7, 2026
Risk Level: SAFE
Full Analysis
- [EXTERNAL_DOWNLOADS]: The skill references installation instructions hosted on GitHub within the inference-sh organization. These references are used to facilitate the setup of tools required for the skill's stated purpose.
- [COMMAND_EXECUTION]: Provides transparent bash examples using the 'belt' CLI to run remote AI applications. These commands are appropriately scoped to video and audio generation tasks.
- [PROMPT_INJECTION]: The skill describes an interface for processing natural language prompts through external tools. This represents a standard use case for creative AI agents and no malicious injection attempts or instructions to bypass safety guidelines were detected.
- Ingestion points: Prompt parameters in 'belt app run' bash examples (SKILL.md).
- Boundary markers: Not present in examples.
- Capability inventory: Execution of the 'belt' CLI via the Bash tool.
- Sanitization: Not demonstrated in the educational examples.
Audit Metadata