algorithmic-art
Pass
Audited by Gen Agent Trust Hub on Mar 1, 2026
Risk Level: SAFEEXTERNAL_DOWNLOADSPROMPT_INJECTION
Full Analysis
- [EXTERNAL_DOWNLOADS]: The skill incorporates the p5.js library via a script tag pointing to Cloudflare's CDN. This is a well-known service and the dependency is required for the skill's functionality.
- [PROMPT_INJECTION]: The skill features a surface for indirect prompt injection by incorporating user input into the art's 'conceptual seed'. * Ingestion points: User instructions are ingested in the philosophy creation and seed deduction steps. * Boundary markers: No explicit delimiters are used to isolate user-provided text from the agent's instructions. * Capability inventory: The skill generates output for browser-based visualization and does not have access to file systems, network shells, or system commands. * Sanitization: User input is treated as a creative seed and is not subjected to formal sanitization.
Audit Metadata