cinema-studio-production
Pass
Audited by Gen Agent Trust Hub on Aug 24, 2026
Risk Level: SAFE
Full Analysis
- [SAFE]: The skill serves as a routing logic layer to delegate cinematic production tasks to specialized sub-skills (LIRA, ACTING, CINEDANCE). It does not contain executable code, remote dependencies, or network operations.
- [INDIRECT_PROMPT_INJECTION]: The skill processes user-supplied scene briefs, dialogue, and metadata. While it handles untrusted external input, it implements data filtering by explicitly stripping historical metadata, asset IDs, and provenance before routing information to downstream specialists.
- Ingestion points: User briefs and cinematic metadata processed in SKILL.md.
- Boundary markers: None explicitly defined for instruction isolation.
- Capability inventory: No direct file system or network access; capabilities are restricted to invoking referenced sub-skills.
- Sanitization: Implements exclusion of sensitive or historical metadata fields.
Audit Metadata