algorithmic-art
Pass
Audited by Gen Agent Trust Hub on Sep 15, 2026
Risk Level: SAFEEXTERNAL_DOWNLOADSINDIRECT_PROMPT_INJECTION
Full Analysis
- [EXTERNAL_DOWNLOADS]: The skill's viewer template fetches the p5.js library from cdnjs.cloudflare.com, which is a well-known and established content delivery network.\n- [EXTERNAL_DOWNLOADS]: The skill connects to fonts.googleapis.com and fonts.gstatic.com to load web fonts, which are official services provided by a trusted organization (Google).\n- [INDIRECT_PROMPT_INJECTION]: The skill uses user input as a foundation for generating both text-based philosophies and executable JavaScript code, creating an inherent attack surface.\n
- Ingestion points: User-provided art prompts and conceptual seeds are ingested to guide the creation of generative sketches.\n
- Boundary markers: The skill does not define specific delimiters or instructions to prevent user-supplied data from being interpreted as agent commands.\n
- Capability inventory: The skill utilizes the Read tool to access template files and generates JavaScript code for execution within a p5.js environment.\n
- Sanitization: There are no documented sanitization or validation steps for user-supplied conceptual inputs before they are incorporated into the generated logic.
Audit Metadata