research-agent

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

• Third-party content exposure detected (high risk: 1.00). The SKILL.md explicitly describes an "autonomous research agent that plans, searches across the web, synthesizes findings, and returns ... with citations," which means it fetches and interprets open/public web content (untrusted third-party sources) as part of its workflow and those sources can influence its actions and outputs.