research-synthesis

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

• Third-party content exposure detected (high risk: 0.90). The SKILL.md explicitly instructs executing external web queries and fetches (e.g., "Step 2: Execute Research Queries" using mcp__Exa__web_search_exa, WebFetch and the Quality Gate requiring "at least 3 external sources"), so untrusted public web content is ingested and used to drive design decisions and follow-on creator actions.