skills/l-yifan/skills/algorithmic-art/Gen Agent Trust Hub

algorithmic-art

Pass

Audited by Gen Agent Trust Hub on Feb 24, 2026

Risk Level: SAFEEXTERNAL_DOWNLOADSPROMPT_INJECTIONREMOTE_CODE_EXECUTION
Full Analysis
  • [EXTERNAL_DOWNLOADS]: Fetches the p5.js library from Cloudflare's CDN (cdnjs.cloudflare.com), which is a well-known and trusted service.\n- [PROMPT_INJECTION]: Instructions mandate repetitive behavioral steering to influence the model persona and encourage the inclusion of hidden 'conceptual seeds' within the generated code.\n- [PROMPT_INJECTION]: The skill provides an indirect prompt injection surface by converting untrusted user descriptions into executable artifacts.\n
  • Ingestion points: User-provided art requests (SKILL.md).\n
  • Boundary markers: Absent.\n
  • Capability inventory: JavaScript execution within browser-based artifacts.\n
  • Sanitization: None; code is generated and embedded directly into a viewer template.\n- [REMOTE_CODE_EXECUTION]: The skill dynamically generates and executes JavaScript code at runtime to render artistic compositions based on user input.
Audit Metadata
Risk Level
SAFE
Analyzed
Feb 24, 2026, 08:17 AM