algorithmic-art
Pass
Audited by Gen Agent Trust Hub on Aug 21, 2026
Risk Level: SAFEEXTERNAL_DOWNLOADSPROMPT_INJECTION
Full Analysis
- [EXTERNAL_DOWNLOADS]: The skill fetches the p5.js library from cdnjs.cloudflare.com and UI fonts from fonts.googleapis.com. Both providers are well-known, trusted services for web resources.
- [PROMPT_INJECTION]: The instructions utilize persona-based directives, such as emphasizing expert craftsmanship and mastery. These are stylistic choices for the creative output and do not represent a bypass of safety guidelines.
- [PROMPT_INJECTION]: The skill exhibits an indirect prompt injection surface by ingesting user descriptions to derive art movements. Ingestion points: user requests for specific art themes; Boundary markers: absent; Capability inventory: generation of client-side JavaScript for artistic visualization; Sanitization: absent. This surface is expected for a generative art tool and is managed by the model's safety guardrails.
- [SAFE]: The skill uses a comprehensive template system to ensure that generated artifacts are self-contained and adhere to a consistent layout, providing a predictable execution environment.
Audit Metadata