blog-writer

Pass

Audited by Gen Agent Trust Hub on Apr 28, 2026

Risk Level: SAFE
Full Analysis
  • [SAFE]: The skill definitions establish a structured workflow for content creation, utilizing markdown as the source of truth and generating Astro components for the final output. It focuses on strategic content planning, SEO optimization, and editorial quality without implementing any high-risk system operations.
  • [INDIRECT_PROMPT_INJECTION]: The skill is designed to ingest and process user-provided summaries and titles which are then interpolated into the content generation pipeline.
  • Ingestion points: User-provided article metadata and summaries described in SKILL.md and references/skill-deep-dive.md.
  • Boundary markers: None explicitly defined in the instructions to isolate untrusted data.
  • Capability inventory: File system writes to the project directory (docs/blogs/ and src/pages/) and invocation of specific layout design tools (SKILL.md).
  • Sanitization: The skill lacks specific instructions for sanitizing or escaping user-provided text before processing, though this is expected given the content generation use case.
  • [COMMAND_EXECUTION]: The workflow incorporates calls to external tools such as the frontend-design plugin for article styling and a photo-management pipeline for asset processing. These tools are used for project-specific development tasks and appear as standard extensions for the target environment.
Audit Metadata
Risk Level
SAFE
Analyzed
Apr 28, 2026, 07:35 AM