The Agent Skills Directory

[SAFE]: No sensitive file access or credential harvesting patterns were identified. The skill only references standard project configuration files for engine detection.
[SAFE]: No evidence of data exfiltration or unauthorized network communication. The skill operates locally on the project structure.
[SAFE]: No obfuscation techniques, hidden characters, or encoded commands were found in the instructions or reference files.
[SAFE]: The skill does not perform remote code execution or package installation; it uses existing files to route the agent to appropriate documentation.
[SAFE]: No prompt injection attempts or instructions to bypass safety filters were detected. The routing logic is clearly defined and focuses on task categorization.

router