cross-validation

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

• Third-party content exposure detected (high risk: 0.90). This skill's SKILL.md explicitly instructs the agent to fetch and parse public third-party sources (e.g., SEC EDGAR JSON at https://data.sec.gov/api/xbrl/companyfacts/..., StockAnalysis pages like https://stockanalysis.com/stocks/{ticker}/financials/, and Gurufocus term pages) and to read/interpret those results to drive discrepancy detection and next actions, which exposes it to untrusted third-party content that could enable indirect prompt injection.