algorithmic-art

Pass

Audited by Gen Agent Trust Hub on Sep 4, 2026

Risk Level: SAFEINDIRECT_PROMPT_INJECTIONEXTERNAL_DOWNLOADS
Full Analysis
  • [INDIRECT_PROMPT_INJECTION]: The skill ingests user-provided aesthetic descriptions to generate JavaScript code. This creates a potential surface for indirect prompt injection if a user provides malicious instructions. However, the risk is mitigated as the output is restricted to a client-side HTML artifact, and the skill enforces the use of a fixed template to constrain the structure of the generated code.
  • [EXTERNAL_DOWNLOADS]: The skill references the p5.js library hosted on Cloudflare's CDN (cdnjs.cloudflare.com) within its HTML template. Cloudflare is a well-known and trusted service, and this reference is standard practice for web-based generative art tools.
Audit Metadata
Risk Level
SAFE
Analyzed
Sep 4, 2026, 03:03 PM
Security Audit — agent-trust-hub — algorithmic-art