scenario-analyzer

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

• Third-party content exposure detected (high risk: 1.00). This skill's Phase 2 (Step 2.1) agent prompt explicitly instructs the scenario-analyst to perform WebSearch to collect related news articles from the past two weeks (public third-party content) and to use those articles to build scenarios and select securities, so untrusted web content can materially influence analysis and tool actions.