algorithmic-art
Pass
Audited by Gen Agent Trust Hub on Jul 2, 2026
Risk Level: SAFEEXTERNAL_DOWNLOADSPROMPT_INJECTION
Full Analysis
- [EXTERNAL_DOWNLOADS]: The skill includes instructions to fetch the p5.js library from Cloudflare's CDN (cdnjs.cloudflare.com), which is a trusted and well-known service.
- [PROMPT_INJECTION]: The skill features a surface for indirect prompt injection as it generates code based on user requests. 1. Ingestion points: User requests for art styles or philosophies defined in SKILL.md. 2. Boundary markers: No specific boundary markers or instructions are provided to the agent to prevent user input from overriding the code generation logic. 3. Capability inventory: The skill produces executable HTML and JavaScript files containing particle system logic. 4. Sanitization: No input validation or sanitization processes are described for the incoming user request.
Audit Metadata