The Agent Skills Directory

[COMMAND_EXECUTION]: Utilizes the Vercel CLI to perform modifications to DNS and domain configuration.
The instructions include the use of the --yes flag with vercel dns rm, which bypasses user confirmation during deletions.
The skill requires the prologe scope for specific operations, interacting with team-level infrastructure.
[INDIRECT_PROMPT_INJECTION]: The skill is designed to read and display external DNS records which could contain malicious or unexpected text payloads.
Ingestion points: The output of vercel dns ls <domain> is processed by the agent.
Boundary markers: No delimiters or protective instructions are provided to help the agent distinguish between data and instructions in DNS record values.
Capability inventory: The skill provides capabilities for further command execution and infrastructure modification based on processed records.
Sanitization: There is no evidence of filtering or sanitizing external DNS record content before it enters the agent's context.

vercel-dns