astrofy-page-design
Pass
Audited by Gen Agent Trust Hub on Oct 12, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTIONEXTERNAL_DOWNLOADSCOMMAND_EXECUTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill ingests external data including content, route objectives, tokens, and components to generate Astro page layouts. This creates a surface where embedded instructions in the source content could potentially influence the agent's behavior.
- Ingestion points: Reads real content, route objectives, tokens, and components from the project environment as specified in SKILL.md and references/technical.md.
- Boundary markers: No specific delimiters or instructions to ignore embedded prompts are defined for the ingested content.
- Capability inventory: The skill is capable of file composition and executing the astrofy check CLI tool for layout verification.
- Sanitization: No explicit sanitization or validation of the ingested content is described before it is used to generate page structures.
- [EXTERNAL_DOWNLOADS]: The skill references documentation from trusted organizations, including the Astro framework (Astro 7.3.3), Tailwind CSS, and the W3C Web Accessibility Initiative. These links are for reference and do not involve remote code execution or untrusted downloads.
- [COMMAND_EXECUTION]: The skill instructs the agent to run the astrofy check command. This tool is part of the vendor's ecosystem (promovaweb) and is used with static parameters for verifying layout integrity, posing no significant security risk in this context.
Audit Metadata