domain-intel

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

• Third-party content exposure detected (low risk: 0.10). The skill queries crt.sh and Google DoH, and performs WHOIS lookups on domains requested by the user, representing active search/fetch of external web and registry data rather than monitored unselected ingress feeds.

MEDIUM W012: Unverifiable external dependency detected (runtime URL that controls agent).

• Potentially malicious external URL detected (high risk: 0.70). The skill makes programmatic requests to external web APIs (crt.sh and Google DNS-over-HTTPS) at runtime, which constitute operational dependencies with unknown or unverified publisher provenance.