financial-research

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 explicitly scrapes and ingests content from public third-party sites (SEC EDGAR via sec.gov and analyst pages on finance.yahoo.com) and directs the agent to parse that content (filings, MD&A guidance, and analyst consensus) to drive outputs and decisions, so untrusted web content can materially influence behavior.