performing-brand-monitoring-for-impersonation

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

• Third-party content exposure detected (high risk: 0.90). The skill directly fetches and parses untrusted public content (e.g., crt.sh Certificate Transparency JSON, play.google.com HTML, rdap.org WHOIS/RDAP responses, and Twitter/X API/profile data) and uses those results to drive findings, severity decisions, reports, and takedown requests, so third‑party content can materially influence behavior.