brand-promo-video-generator
Pass
Audited by Gen Agent Trust Hub on Nov 4, 2026
Risk Level: SAFE
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill processes untrusted data from user-supplied links and external brand websites.
- Ingestion points:
webfetchis used in Step 1 and Step 2 to gather brand facts, logos, and typography from external URLs. - Boundary markers: The skill implements a mandatory 'hard confirmation' gate (Step 7) where the agent must present a pre-production package and receive explicit user approval before proceeding to generation.
- Capability inventory: The skill has access to media generation and editing tools such as
hub_generate_videoandhub_video_editto produce the final output. - Sanitization: The instructions require the agent to build a brand truth sheet and a provenance manifest to track asset authenticity, with a final verification step (Step 9) to ensure no unauthorized or imitation assets are included in the delivery.
Audit Metadata