multi-clips-to-reels
Pass
Audited by Gen Agent Trust Hub on Oct 23, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill processes untrusted external data as a core part of its video editing workflow, which creates a surface for indirect prompt injection attacks.
- Ingestion points: The agent ingests user-supplied scripts, storyboards, scene notes, and asset metadata via the
read_scripttool and manual review (SKILL.md, steps 3, 7, and 8). - Boundary markers: The instructions do not specify the use of delimiters (e.g., XML tags or triple quotes) or provide 'ignore instructions' warnings when the agent processes these external script files.
- Capability inventory: The skill utilizes video project management tools (
open_media_reel), asset inspection (view_asset_frames), script reading (read_script), and timeline editing commands. - Sanitization: No evidence of input validation, filtering, or escaping was found in the instructions for handling the external script content.
Audit Metadata