The Agent Skills Directory

[INDIRECT_PROMPT_INJECTION]: The skill processes untrusted data from the website being diagnosed, creating a surface for potential injection attacks.
Ingestion points: The agent reads runtime logs via hosting_nodejs_runtime-logs, build outputs via hosting_get-deployment, and configuration files via hosting_files_website-content.
Boundary markers: The instructions do not specify the use of delimiters or clear directives for the agent to ignore instructions embedded within the logs or file content.
Capability inventory: The skill has the ability to modify server settings and application states, including hosting_php_update-options, hosting_ssl_toggle-https-redirect, hosting_nodejs_restart-application, and wordpress_plugins_deactivate.
Sanitization: There is no mention of sanitizing or validating external content before it is processed by the agent.
[COMMAND_EXECUTION]: The skill utilizes standard command-line tools to gather external diagnostic information about the target domain.
Evidence: The agent is instructed to execute curl to check HTTP status codes and headers, and dig to verify DNS records (A, NS, and CAA).

troubleshoot-website