The Agent Skills Directory

[COMMAND_EXECUTION]: The skill utilizes standard system utilities dig and curl for network diagnostics and domain resolution verification. These tools are used for their intended purpose within the scope of domain management and do not involve shell injection or execution of untrusted scripts.
[INDIRECT_PROMPT_INJECTION]: The skill processes external data by reading DNS records and HTTP headers from the domain being configured. While this presents a theoretical attack surface for indirect prompt injection, it is mitigated by explicit instructions requiring the agent to obtain user confirmation before making any changes.
Ingestion points: DNS record values (MX, TXT, CAA, etc.) and HTTP response headers retrieved via dig and curl.
Boundary markers: The skill does not use specific delimiters but instructs the agent to "State the change and get a yes before each one."
Capability inventory: The skill can modify DNS records, update hosting settings, and install SSL certificates via the Hostinger Connector tools.
Sanitization: No explicit content sanitization is mentioned; security relies on the human-in-the-loop confirmation process.

connect-domain