astrofy-sections
Pass
Audited by Gen Agent Trust Hub on Oct 12, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTIONCOMMAND_EXECUTIONEXTERNAL_DOWNLOADS
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill is designed to analyze and modify project source code, which constitutes an ingestion point for potentially untrusted data.
- Ingestion points: The skill reads existing component files, project configuration at
.astrofy/config/paths.json, and typed content from the local environment. - Boundary markers: There are no explicit instructions for the agent to use delimiters or ignore instructions embedded in the project files.
- Capability inventory: The agent performs file reads and executes project-specific commands in the terminal.
- Sanitization: The instructions explicitly include a security best practice to sanitize external content before converting it to HTML.
- [COMMAND_EXECUTION]: The skill directs the agent to execute a validation command using the
astrofyCLI tool (astrofy check --category components). This tool appears to be a vendor-specific utility for component auditing. - [EXTERNAL_DOWNLOADS]: The skill references official and well-known documentation sources for technical guidance.
- Evidence: Links are provided to Mozilla Developer Network (developer.mozilla.org), Astro documentation (docs.astro.build), and Tailwind CSS (tailwindcss.com). These references are for documentation purposes and are categorized as trusted sources.
Audit Metadata