algorithmic-art

Pass

Audited by Gen Agent Trust Hub on Feb 27, 2026

Risk Level: SAFEEXTERNAL_DOWNLOADSPROMPT_INJECTION
Full Analysis
  • [EXTERNAL_DOWNLOADS]: The viewer.html template fetches the p5.js library from Cloudflare's well-known cdnjs service.
  • [PROMPT_INJECTION]: The skill utilizes instructional emphasis and repetition (e.g., 'meticulously crafted') to guide the AI agent's creative persona.
  • [PROMPT_INJECTION]: The skill incorporates an indirect prompt injection surface by processing user-provided concepts. 1. Ingestion points: User instructions in the generative art request. 2. Boundary markers: Not explicitly defined in the prompt instructions. 3. Capability inventory: Limited to generating client-side p5.js/HTML artifacts with no server-side or filesystem access. 4. Sanitization: No specific input sanitization is defined for the derived conceptual seeds.
Audit Metadata
Risk Level
SAFE
Analyzed
Feb 27, 2026, 12:39 AM