The Agent Skills Directory

[INDIRECT_PROMPT_INJECTION]: The skill processes untrusted user input in the form of a domain name to check DNS records. There is a potential risk if the input is not sanitized before being executed in the shell.
Ingestion points: The <domain> parameter provided by the user in SKILL.md.
Boundary markers: None present; the instructions do not specify using delimiters or warnings to ignore instructions embedded in the domain data.
Capability inventory: The skill utilizes a bash tool to execute dns records and jq commands.
Sanitization: No explicit sanitization or validation logic is provided to ensure the domain string does not contain command injection characters.
[COMMAND_EXECUTION]: The skill relies on shell command execution to perform its primary function.
Evidence: Instructions direct the agent to use dns records <domain> and jq within a shell environment provided by an external MCP.

email-deliverability