client-meeting-prep-agent

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

• Third-party content exposure detected (high risk: 0.90). The skill's required workflow and Information Sources & Search Strategy explicitly instruct the agent to perform web searches and scrape LinkedIn/social media plus public web pages (e.g., "Web Search" and "LinkedIn / Social Media" sections and Phase 1: Research Gathering), meaning the agent will ingest untrusted, user-generated third‑party content and synthesize it into recommendations that can change tool use and decisions.