Skills
Navigate
skills/magichourhq/skills/magic-hour-ad-variants/Gen Agent Trust Hub

magic-hour-ad-variants

Pass

Audited by Gen Agent Trust Hub on Nov 3, 2026

Risk Level: SAFEEXTERNAL_DOWNLOADSINDIRECT_PROMPT_INJECTION
Full Analysis
  • [EXTERNAL_DOWNLOADS]: The skill connects to the vendor's production infrastructure at mcp.magichour.ai and references official API documentation at docs.magichour.ai to facilitate video generation.
  • [INDIRECT_PROMPT_INJECTION]: The skill processes external inputs such as video transcripts, product references, and user-supplied ad copy. It addresses potential injection risks by providing specific instructions to the agent to avoid inventing quotations, results, or pricing, and to stick strictly to supplied product facts.
Audit Metadata
Risk Level
SAFE
Analyzed
Nov 3, 2026, 03:22 AM