algorithmic-art

Pass

Audited by Gen Agent Trust Hub on Feb 28, 2026

Risk Level: SAFEPROMPT_INJECTIONEXTERNAL_DOWNLOADS
Full Analysis
  • [PROMPT_INJECTION]: The skill uses aggressive instructional reinforcement, such as "CRITICAL" and "REPEATEDLY emphasize," to force the AI into an "expert craftsmanship" persona. This is a form of behavioral manipulation designed to make the output appear more authoritative than its actual capability.
  • [PROMPT_INJECTION]: The skill provides an indirect prompt injection surface.
  • Ingestion points: User-provided "subtle input or instructions" are used as the foundation for both the "Algorithmic Philosophy" and the implementation code in SKILL.md.
  • Boundary markers: None. There are no instructions to disregard or sanitize malicious directives that might be embedded in the user's creative request.
  • Capability inventory: The skill generates interactive HTML/JS artifacts that execute code in the browser via p5.js.
  • Sanitization: Absent. User-supplied concepts are translated into code logic without validation.
  • [EXTERNAL_DOWNLOADS]: The templates/viewer.html file references the p5.js library from Cloudflare's CDN (cdnjs.cloudflare.com). This is documented as a neutral finding as it uses a well-known and trusted technology service.
Audit Metadata
Risk Level
SAFE
Analyzed
Feb 28, 2026, 10:51 AM