security-posture-analyzer

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

• Third-party content exposure detected (high risk: 1.00). The skill explicitly consumes and parses untrusted public web and DNS content—e.g., signals.http_signals.headers (Content-Security-Policy), signals.dns_signals.txt_records (SPF/DMARC/DKIM), and get_file_content(signals, "/.well-known/security.txt")—and uses that parsed third-party content (CSP domains, security.txt contents, DNS records) to drive technology detection, scoring, and recommendations, so external content can materially influence agent decisions.