drama-series-writing
Pass
Audited by Gen Agent Trust Hub on Oct 30, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill is designed to ingest user-supplied creative ideas and briefs which are then processed into structured formats like 'Story DNA' and 'Season arcs.' This interaction model creates a surface where user content is interpolated into agent instructions without explicit security boundaries.
- Ingestion points: User-provided professions, settings, and narrative briefs are integrated into the Story DNA and episode beats in
SKILL.md. - Boundary markers: The skill does not define specific delimiters or instructions for the agent to ignore embedded commands within user content.
- Capability inventory: The skill does not request or use high-risk capabilities such as network access, shell execution, or file system writing.
- Sanitization: The instructions 'Preserve a typed profession...' and 'Carry the user's words through unchanged' indicate that user input is processed directly without sanitization.
Audit Metadata