The Agent Skills Directory

[COMMAND_EXECUTION]: The skill instructs the agent to execute shell commands such as dig and curl using a DOMAIN variable. If the domain name provided by the user or retrieved from the system is not properly sanitized by the agent's execution environment, it creates a surface for shell command injection attacks.
[INDIRECT_PROMPT_INJECTION]: The skill fetches data from external sources, specifically DNS records (A, MX, TXT, etc.), to determine configuration steps. Because these records are controlled by external entities, they could be crafted to contain malicious instructions aimed at influencing the agent's behavior.
Ingestion points: Public DNS records retrieved via dig (Step 1 and 5) and the dns_records_list operation (Step 3).
Boundary markers: The instructions do not define specific delimiters or ignore-instructions for the content retrieved from DNS records.
Capability inventory: The skill possesses significant capabilities including modifying DNS zones (dns_records_update), creating websites (hosting_websites_create), and executing network/diagnostic commands.
Sanitization: No explicit sanitization or content validation is required by the instructions before the agent processes or preserves external DNS record values.

connect-domain