chuinb

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

• Third-party content exposure detected (high risk: 0.90). The skill's mandatory execution flow explicitly requires live web research and ingestion—Phase 2 ("Deep Research") mandates using WebSearch and WebFetch to fetch public webpages and articles, and Phase 3 ("Media Acquisition") requires downloading images/videos from external sources (media-downloader, YouTube, Pexels) which are untrusted third‑party content that the agent reads and incorporates into its outputs and decision-making.