sound-design
Pass
Audited by Gen Agent Trust Hub on Sep 19, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTIONNO_CODE
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill processes external production documents (screenplays, shot briefs) which could serve as a vector for indirect prompt injection. However, the risk is negligible as the skill only writes structured metadata to a local file.
- Ingestion points: Reading core contract, screenplay, shot briefs, and continuity in SKILL.md.
- Boundary markers: None used for external data.
- Capability inventory: Writes JSONL cues to the local filesystem.
- Sanitization: None.
- [NO_CODE]: The skill consists exclusively of markdown instructions and workflow descriptions without any associated scripts or binary files.
Audit Metadata