algorithmic-art
Pass
Audited by Gen Agent Trust Hub on Sep 8, 2026
Risk Level: SAFEEXTERNAL_DOWNLOADSINDIRECT_PROMPT_INJECTION
Full Analysis
- [EXTERNAL_DOWNLOADS]: The skill's HTML template (
templates/viewer.html) and requirements (sub-skills/required-features.md) reference the p5.js library via Cloudflare's CDN athttps://cdnjs.cloudflare.com/ajax/libs/p5.js/1.7.0/p5.min.js. This is a standard and safe practice for providing web-based generative art capabilities. - [INDIRECT_PROMPT_INJECTION]: The skill processes user-supplied aesthetic concepts to generate an 'algorithmic philosophy' and subsequent code artifacts. This creates a surface where external data influences the generated output. 1. Ingestion points: User instructions as specified in
sub-skills/the-critical-understanding.md. 2. Boundary markers: Instructions suggest using user input as a foundation while maintaining creative freedom. 3. Capability inventory: The skill generates HTML and JavaScript code meant for interactive execution in an artifact viewer. 4. Sanitization: There is no explicit description of sanitization or validation of user-provided strings before they are incorporated into the generated logic.
Audit Metadata