motion-graphics

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

• Third-party content exposure detected (medium risk: 0.30). The required workflow for source-backed motion graphics (such as web pages, news articles, and tweets) monitors or consumes outsider-authored free text via ingestion steps described in SKILL.md and category modules like categories/webpage/module.md, categories/news/module.md, and categories/tweet/module.md without the agent first selecting a specific item.

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

• Potentially malicious external URL detected (high risk: 0.70). The skill contains instructions and code templates that fetch map, chart, and UI rendering libraries from jsDelivr, map tiles from ArcGIS and CARTO, and geographical datasets from unauthenticated remote endpoints during execution.