essay-authoring
Pass
Audited by Gen Agent Trust Hub on May 13, 2026
Risk Level: SAFE
Full Analysis
- [SAFE]: The skill serves as a style guide and architectural template for creating MDX-based content. It defines visual patterns (scrollytelling), component usage (Callouts, Scenes), and editorial standards.
- [SAFE]: No external dependencies are introduced. The instructions refer to existing local project directories such as
components/mdx/for registering components. - [SAFE]: The voice guardrails and checklist focus on maintaining consistency and preventing common LLM-generated writing tropes (e.g., 'tricolon overuse', 'dramatic closers') and do not contain instructions to bypass agent safety filters.
- [SAFE]: Examples of embedded media (iframes) are provided as documentation for standard web features and do not point to malicious domains or involve exfiltration logic.
Audit Metadata