algorithmic-art

Pass

Audited by Gen Agent Trust Hub on Jul 16, 2026

Risk Level: SAFEPROMPT_INJECTIONEXTERNAL_DOWNLOADS
Full Analysis
  • [PROMPT_INJECTION]: The skill instructs the agent to process user-supplied 'conceptual seeds' and instructions to generate both an algorithmic philosophy and the resulting p5.js code. This creates an indirect prompt injection surface.\n * Ingestion points: User input and instructions described in the 'DEDUCING THE CONCEPTUAL SEED' and 'ALGORITHMIC PHILOSOPHY CREATION' sections (SKILL.md).\n * Boundary markers: Absent; there are no instructions to use specific delimiters or to warn the agent against executing instructions embedded within the user's creative requests.\n * Capability inventory: The skill generates and outputs .md, .html, and .js files which are rendered as interactive artifacts, providing a mechanism for code delivery to the user.\n * Sanitization: No evidence of sanitization or validation of user-provided content is present in the skill instructions.\n- [EXTERNAL_DOWNLOADS]: The generated art artifacts include a script reference to the p5.js library hosted on Cloudflare's CDNJS (cdnjs.cloudflare.com), which is a well-known and established service for web development.
Audit Metadata
Risk Level
SAFE
Analyzed
Jul 16, 2026, 08:08 AM
Security Audit — agent-trust-hub — algorithmic-art