episode-writing
Pass
Audited by Gen Agent Trust Hub on Jun 29, 2026
Risk Level: SAFE
Full Analysis
- [SAFE]: The skill implements a structured workflow for creative writing using project-local artifacts. Workflow: 1. Ingestion points: Reads 'outline' and 'characters' artifacts via MCP load_artifact (SKILL.md). 2. Boundary markers: Absent. 3. Capability inventory: Uses Write tool to create Markdown files and log_decision for metadata (SKILL.md). 4. Sanitization: Absent. Although it processes external data, the context is creative scriptwriting with no high-risk capabilities triggered by the content.
- [SAFE]: Content boundaries explicitly forbid technical cinematic terms, focusing the agent on narrative creation.
- [SAFE]: No network operations, external downloads, or execution of untrusted code detected.
Audit Metadata