outline-coach
Pass
Audited by Gen Agent Trust Hub on Feb 25, 2026
Risk Level: SAFENO_CODE
Full Analysis
- [SAFE]: The skill is purely instructional and consists of markdown text providing a persona and framework for the AI agent. It does not include scripts, binaries, or commands that interact with the system shell or network.
- [NO_CODE]: There is no code shipped with this skill. It relies on the agent's natural language processing capabilities to follow the provided coaching methodology.
- [PROMPT_INJECTION]: The skill is designed to process user-provided story content, which presents a surface for indirect prompt injection. However, the risk is negligible as the skill lacks high-privilege capabilities such as code execution or remote network requests. Evidence: 1. Ingestion points: User-provided story outlines and the local file
context/output-config.md; 2. Boundary markers: None specified; 3. Capability inventory: Local file writing for session persistence; 4. Sanitization: None.
Audit Metadata