algorithmic-art
Pass
Audited by Gen Agent Trust Hub on Sep 19, 2026
Risk Level: SAFEEXTERNAL_DOWNLOADSINDIRECT_PROMPT_INJECTION
Full Analysis
- [EXTERNAL_DOWNLOADS]: The skill's HTML viewer template fetches the p5.js library from Cloudflare's content delivery network (cdnjs) and fonts from Google's font service.
- [INDIRECT_PROMPT_INJECTION]: The skill processes user-supplied creative inputs and instructions to generate executable code artifacts (HTML and JavaScript).
- Ingestion points: User prompts and creative descriptions processed in SKILL.md.
- Boundary markers: None specified for user input separation.
- Capability inventory: Generates interactive HTML/JS artifacts for browser execution.
- Sanitization: The skill relies on standard agent behavior and does not specify explicit sanitization for embedded user concepts.
Audit Metadata