algorithmic-art

Pass

Audited by Gen Agent Trust Hub on Jun 27, 2026

Risk Level: SAFEEXTERNAL_DOWNLOADSPROMPT_INJECTIONCOMMAND_EXECUTION
Full Analysis
  • [EXTERNAL_DOWNLOADS]: The skill's HTML viewer template fetches the p5.js library from Cloudflare's CDN (cdnjs.cloudflare.com) and typography resources from Google Fonts (fonts.googleapis.com, fonts.gstatic.com). These are well-known and trusted technology services.
  • [PROMPT_INJECTION]: The skill contains instructions that require the agent to adopt a deceptive persona, repeatedly asserting that the generated code is the result of 'deep computational expertise' and 'painstaking optimization' regardless of the actual implementation details.
  • [PROMPT_INJECTION]: The skill is susceptible to indirect prompt injection due to its architecture.
  • Ingestion points: User-supplied aesthetic prompts and conceptual seeds are used to influence code generation.
  • Boundary markers: No specific delimiters or safety warnings for embedded instructions are present in the generation logic.
  • Capability inventory: The skill possesses the ability to generate and execute arbitrary JavaScript within an interactive browser artifact.
  • Sanitization: There are no instructions for sanitizing or escaping user-supplied content before it is interpolated into the generated executable code.
  • [COMMAND_EXECUTION]: The skill is designed to generate and execute JavaScript logic to produce generative art, representing its core intended functionality.
Audit Metadata
Risk Level
SAFE
Analyzed
Jun 27, 2026, 11:03 AM
Security Audit — agent-trust-hub — algorithmic-art