mira-anime
Pass
Audited by Gen Agent Trust Hub on Oct 11, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill processes user-supplied descriptions and reference photos to generate prompts for external image and video generation tools.
- Ingestion points: User inputs describing the scene, reference photos, and interview responses in SKILL.md.
- Boundary markers: No explicit delimiters are used to wrap external content.
- Capability inventory: The skill instructs the agent to invoke generate_video and generate_image tools.
- Sanitization: The instructions include a 'Checklist' and 'Do not' sections that guide the agent to filter out photographic terminology and copyrighted names, and to transform descriptions into a specific technical format.
Audit Metadata