algorithmic-art
Pass
Audited by Gen Agent Trust Hub on Sep 21, 2026
Risk Level: SAFEEXTERNAL_DOWNLOADSINDIRECT_PROMPT_INJECTION
Full Analysis
- [SAFE]: The skill implements a legitimate workflow for generative art creation. The instructions emphasize craftsmanship and adherence to a specific template structure.
- [EXTERNAL_DOWNLOADS]: The
templates/viewer.htmlfile references external assets from well-known services. It fetches the p5.js library fromcdnjs.cloudflare.comand loads typography from Google Fonts (fonts.googleapis.comandfonts.gstatic.com). - [INDIRECT_PROMPT_INJECTION]: The skill ingests user input to deduce a conceptual seed for the generative art. • Ingestion points: User instructions or original requests processed to identify a conceptual thread (SKILL.md). • Boundary markers: None explicitly defined for user-provided strings within the deduction process. • Capability inventory: The skill generates self-contained HTML and JavaScript artifacts for browser execution. • Sanitization: No specific sanitization or escaping is mentioned for conceptual seeds when interpolated into the generated algorithm.
Audit Metadata