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