algorithmic-art

Pass

Audited by Gen Agent Trust Hub on Apr 18, 2026

Risk Level: SAFEEXTERNAL_DOWNLOADSPROMPT_INJECTION
Full Analysis
  • [EXTERNAL_DOWNLOADS]: The viewer.html template references the p5.js library from Cloudflare's CDN (cdnjs.cloudflare.com) and fonts from Google (fonts.googleapis.com). These are established technology services used for legitimate front-end development.
  • [PROMPT_INJECTION]: The skill processes user instructions to generate an 'Algorithmic Philosophy' and subsequent HTML/JS code. This constitutes an indirect prompt injection surface as untrusted user input influences the generated code artifact.
  • Ingestion points: User instructions or conceptual seeds processed in SKILL.md.
  • Boundary markers: None explicitly defined to separate user input from system instructions.
  • Capability inventory: Generation of interactive HTML and JavaScript artifacts.
  • Sanitization: None specified for user-provided strings when interpolated into the artifact title or philosophy description.
  • [SAFE]: No patterns for credential theft, sensitive file access, or unauthorized command execution were found. The skill operates within the expected parameters of a creative coding tool.
Audit Metadata
Risk Level
SAFE
Analyzed
Apr 18, 2026, 12:07 PM
Security Audit — agent-trust-hub — algorithmic-art