The Agent Skills Directory

[SAFE]: The skill performs legitimate website monitoring tasks including uptime, performance, and security checks (TLS/SSL) as described in its documentation.
[SAFE]: External communication is limited to well-known services (Google Chrome UX Report API) and the specific business URL configured in the local environment.
[SAFE]: The formDelivers function implements a security check to verify the target URL's origin matches the configured business.url before transmitting the LEAD_TEST_SECRET, preventing accidental or malicious exfiltration to third-party domains.
[INDIRECT_PROMPT_INJECTION]: The skill processes untrusted data from external websites which presents a potential attack surface for indirect prompt injection.
Ingestion points: External website URLs (site, origin), sitemap XML content, and TLS certificate metadata.
Boundary markers: The skill includes logic to validate target origins against the internal business.url configuration.
Capability inventory: The skill utilizes network capabilities (fetch, tls.connect) and interacts with lead data (getLead, sendAlert).
Sanitization: Employs origin matching to ensure secrets are only sent to the authorized business endpoint.

launch-site-health-report