algorithmic-art
Pass
Audited by Gen Agent Trust Hub on Oct 6, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTIONEXTERNAL_DOWNLOADS
Full Analysis
- [EXTERNAL_DOWNLOADS]: The skill fetches the p5.js library from Cloudflare's public CDN (cdnjs.cloudflare.com) to enable generative art functionality.
- [INDIRECT_PROMPT_INJECTION]: The skill processes user-provided instructions to influence the generation of algorithmic philosophies and JavaScript code, creating an attack surface where malicious input could potentially influence the resulting artifact.
- Ingestion points: User requests and instructions provided at runtime are used as the foundation for generative art concepts.
- Boundary markers: No specific delimiters or safety warnings are implemented when interpolating user concepts into the generative philosophy or code.
- Capability inventory: The skill generates interactive HTML and JavaScript artifacts that execute within the user's browser environment.
- Sanitization: The instructions do not specify sanitization or validation steps for the user-supplied conceptual threads before they are integrated into the algorithm.
Audit Metadata