algorithmic-art

Pass

Audited by Gen Agent Trust Hub on Apr 28, 2026

Risk Level: SAFEEXTERNAL_DOWNLOADSPROMPT_INJECTION
Full Analysis
  • [EXTERNAL_DOWNLOADS]: The skill references the p5.js library via a script tag pointing to Cloudflare's CDN and uses Google Fonts. Both are well-known and reputable third-party services.
  • [PROMPT_INJECTION]: The skill's architecture involves processing user-provided requests to generate generative art code. This creates a surface for indirect prompt injection where user input could influence the generated logic. However, the instructions focus on creative expression and do not contain patterns for bypassing safety guidelines or extracting sensitive information.
  • [SAFE]: The skill includes a non-functional numeric string '6877532' in the SKILL.md file, which appears to be an artifact of the development process rather than a malicious command or encoded data. The overall structure adheres to best practices for artifact generation, including the use of seeded randomness and structured parameters.
Audit Metadata
Risk Level
SAFE
Analyzed
Apr 28, 2026, 10:49 PM
Security Audit — agent-trust-hub — algorithmic-art