market-report-pdf

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

• Third-party content exposure detected (high risk: 0.90). This skill explicitly instructs the agent to analyze an arbitrary public URL using scripts/analyze_page.py ("If the user insists on generating a report without prior audits, analyze the provided URL directly and build the data structure from scratch" in Step 1), meaning it fetches and ingests untrusted third‑party web content which is then used to drive scores, findings, and actions in the generated report.