add-thinker

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

• Third-party content exposure detected (high risk: 1.00). The skill's Phase 2 research agent prompts (e.g., "Agent 1: Primary Source Researcher" and others) explicitly instruct using WebSearch and WebFetch to retrieve primary sources, case studies, interviews and specific URLs and to report quotes and source URLs, so the agent will ingest untrusted public web content that can influence generation and behavior.