algorithmic-art
Pass
Audited by Gen Agent Trust Hub on Sep 14, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTIONEXTERNAL_DOWNLOADS
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill processes user-provided conceptual art requests to generate algorithmic philosophies and p5.js code. This represents a standard surface for indirect prompt injection where untrusted user input influences generated executable content.
- Ingestion points: User prompts interpreted by the agent in
SKILL.md. - Boundary markers: Absent; the skill relies on natural language instructions to guide interpretation.
- Capability inventory: The skill generates self-contained HTML/JS artifacts for browser execution.
- Sanitization: Absent.
- [EXTERNAL_DOWNLOADS]: The
templates/viewer.htmlfile includes references to external resources from well-known and trusted services. - Evidence: Fetches the p5.js library from
cdnjs.cloudflare.comand fonts fromfonts.googleapis.comandfonts.gstatic.com. These are reputable infrastructure providers used for the skill's intended visual output.
Audit Metadata