lecture-site-engine

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

• Third-party content exposure detected (high risk: 0.75). The required workflow for banner-design includes runtime browser research on Pinterest (an outsider-authored public web source), and the agent uses the resulting reference pins to inform its drafting/generation steps, which can introduce free-text prompt content 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 skill includes an explicit runtime script tag that loads and executes remote JavaScript from the Chart.js CDN (https://cdn.jsdelivr.net/npm/chart.js@4.4.1/dist/chart.umd.min.js), which will be fetched during preview/export and is a required dependency for chart rendering.