algorithmic-art

MEDIUM W011: Third-party content exposure detected (indirect prompt injection risk).

• Third-party content exposure detected (medium risk: 0.30). The runtime workflow reads a user-influenced seed-input value (free text via the HTML number input) and uses it in initializeSystem() via randomSeed(params.seed) / noiseSeed(params.seed), so outsider-authored text provided through the artifact UI is ingested directly into the LLM context.

MEDIUM W012: Unverifiable external dependency detected (runtime URL that controls agent).

• Potentially malicious external URL detected (high risk: 0.80). The template includes a runtime script tag that fetches and executes remote JavaScript from https://cdnjs.cloudflare.com/ajax/libs/p5.js/1.7.0/p5.min.js, which is a required dependency for the artifact and will run code in the execution environment.