algorithmic-art
Pass
Audited by Gen Agent Trust Hub on Apr 13, 2026
Risk Level: SAFEEXTERNAL_DOWNLOADS
Full Analysis
- [EXTERNAL_DOWNLOADS]: The skill fetches the p5.js library from Cloudflare's well-known CDN (cdnjs.cloudflare.com), which is standard practice for generative art projects.
- [EXTERNAL_DOWNLOADS]: The skill loads design assets and typography from Google Fonts (fonts.googleapis.com and fonts.gstatic.com).
- [INDIRECT_PROMPT_INJECTION]: The skill accepts user instructions to guide the creation of generative art. While this involves processing untrusted data to generate code, the instructions prioritize artistic expression and use structured templates to minimize injection risks.
- Ingestion points: User-provided art descriptions and parameters processed via the instructions in SKILL.md.
- Boundary markers: The prompt provides clear structural boundaries for the generated output, though explicit markers for user-input isolation are not used.
- Capability inventory: The skill generates HTML and JavaScript artifacts designed for execution within a browser-based sandbox environment.
- Sanitization: Relies on the AI agent's internal safety guardrails during the code generation process.
Audit Metadata