media-qc
Pass
Audited by Gen Agent Trust Hub on Sep 19, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill processes external project documentation and media references which represents an indirect prompt injection surface.
- Ingestion points: The skill reads the core contract, shot briefs, take records, and approved references (SKILL.md).
- Boundary markers: No boundary markers or delimiters are defined to separate ingested data from agent instructions.
- Capability inventory: The skill performs file system reads and has write access to the '04_generation/take_qc.jsonl' file.
- Sanitization: The workflow does not include specifications for validating or sanitizing the content of the ingested project files.
Audit Metadata