algorithmic-art
Pass
Audited by Gen Agent Trust Hub on Sep 30, 2026
Risk Level: SAFEEXTERNAL_DOWNLOADSINDIRECT_PROMPT_INJECTIONDYNAMIC_EXECUTION
Full Analysis
- [EXTERNAL_DOWNLOADS]: The skill's HTML viewer template fetches the
p5.jslibrary fromcdnjs.cloudflare.com. This is a well-known and trusted service for hosting web libraries. - [INDIRECT_PROMPT_INJECTION]: The skill possesses an indirect injection surface as it processes user-supplied aesthetic instructions to generate code. Evidence chain:
- Ingestion points: User-provided creative prompts and instructions processed in
SKILL.md. - Boundary markers: The skill lacks explicit markers or delimiters to isolate user instructions from the generation logic.
- Capability inventory: The skill generates and executes JavaScript code within an interactive HTML artifact viewer.
- Sanitization: No specific sanitization or validation logic is defined for the user-supplied conceptual inputs.
- [DYNAMIC_EXECUTION]: The skill generates interactive JavaScript code (p5.js) based on an 'algorithmic philosophy' derived from user requests. This generation is contained within a restricted HTML template provided by the skill, which enforces a specific structure, parameters, and branding.
Audit Metadata