The Agent Skills Directory

[SAFE]: The skill contains purely instructional text for a specialized interaction mode. No malicious command execution, network exfiltration, or obfuscation was found.
[SAFE]: The instruction to check the codebase for answers is a standard functional request for AI agent tools and does not introduce security risks beyond the agent's existing workspace permissions.
[SAFE]: No hardcoded credentials, sensitive file path access, or persistence mechanisms were identified in the skill instructions.

deep-probe