The Agent Skills Directory

[SAFE]: The skill facilitates website audits through the vendor's official endpoint at https://www.developh.co/mcp. These network operations are consistent with the skill's stated purpose and use the vendor's own infrastructure.
[SAFE]: The request_contact tool, which handles user name and email, is governed by strict instructions requiring the agent to obtain explicit user consent and show the message before sending, preventing unauthorized data exfiltration.
[SAFE]: A provided command-line example demonstrates how to call the API manually. The command uses a benign Python one-liner to parse JSON output and does not perform any dangerous remote code execution or file system modifications.

website-audit