astro-content
Pass
Audited by Gen Agent Trust Hub on Feb 21, 2026
Risk Level: SAFE
Full Analysis
- [SAFE] (SAFE): The skill follows standard development practices for Astro/Starlight content management. It performs local file operations (creating MDX files and updating a TypeScript configuration) within the project's directory structure.
- [Indirect Prompt Injection] (LOW): The skill acts as a content generator based on user input, which is a potential surface for indirect prompt injection if the generated content is later processed by other automated tools.
- Ingestion points: User-provided article title, description, and body content entering via the chat interface.
- Boundary markers: Absent; the skill directly interpolates user strings into YAML frontmatter and MDX body templates.
- Capability inventory: File-write access to
app/src/content/docs/andapp/src/sidebar.ts. - Sanitization: Absent; the skill relies on the agent's default safety filters for content generation.
Audit Metadata