Music Video
Pass
Audited by Gen Agent Trust Hub on Nov 1, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill processes user-controlled data (lyrics, themes, and audio) that are used as inputs for downstream media generation tools, creating a surface for indirect prompt injection.
- Ingestion points: User-supplied lyrics, themes, and visual premises are ingested as primary inputs in the 'Required inputs' section of
SKILL.md. - Boundary markers: There are no explicit delimiters or instructions provided to the agent to ignore or sanitize instructions embedded within the user-provided lyrics or themes.
- Capability inventory: The skill leverages powerful media generation capabilities including
media.generate_music,media.generate_image, andmedia.generate_video. - Sanitization: The instructions lack specific sanitization steps or validation logic for external strings before they are incorporated into generation prompts.
Audit Metadata