mockumentary-structure
Pass
Audited by Gen Agent Trust Hub on Oct 9, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill is designed to ingest and process user-supplied creative content, which presents a surface for indirect prompt injection attacks.\n
- Ingestion points: User project descriptions, act structure plans, and pacing discussions.\n
- Boundary markers: The instructions lack explicit delimiters or instructions to treat user-provided data as untrusted content.\n
- Capability inventory: The skill directs the agent to write to 'script/outline.md' and 'script/treatment.md'.\n
- Sanitization: No content filtering or sanitization processes are defined for the processed user data.
Audit Metadata