algorithmic-art
Pass
Audited by Gen Agent Trust Hub on Mar 9, 2026
Risk Level: SAFE
Full Analysis
- [EXTERNAL_DOWNLOADS]: The skill fetches the p5.js library from Cloudflare's CDNJS and font assets from Google Fonts. These are established, well-known services used for their intended purposes.
- [COMMAND_EXECUTION]: The skill generates interactive HTML artifacts containing client-side JavaScript (p5.js). This is the primary function of the skill and is handled through a static template that restricts the execution environment to the user's browser.
- [PROMPT_INJECTION]: The skill identifies a surface for indirect prompt injection as it processes user requests to derive 'conceptual seeds' for the generated code.
- Ingestion points: User-provided artistic prompts and aesthetic instructions in SKILL.md.
- Boundary markers: Absent; the skill relies on creative interpretation rather than strict delimiters.
- Capability inventory: Generation of p5.js code and HTML artifacts as defined in templates/viewer.html.
- Sanitization: No explicit sanitization logic is provided in the instructions, relying instead on the model's internal safety guardrails.
Audit Metadata