The Agent Skills Directory

[SAFE]: The skill consists of documentation and instructions for an AI agent to manage account connections. It does not contain any executable code, scripts, or external dependencies.
[SAFE]: No data exfiltration or credential exposure patterns were found. The documentation explicitly states that credentials are stored in a secure vault and are never returned by APIs or accepted as direct input.
[SAFE]: No prompt injection or obfuscation techniques were detected. The language is purely instructional and follows platform-standard patterns.
[SAFE]: The skill includes security-conscious guidance, such as instructing the agent to perform an offboarding preflight check and hand off sensitive resolution steps to a human-controlled web application rather than attempting automated resolution of private connection boundaries.

elaichi-connections