The Agent Skills Directory

[SAFE]: The skill is composed entirely of natural language instructions providing a behavioral framework ('posture') for the agent. It does not contain any executable scripts, shell commands, or binary files.
[SAFE]: No patterns associated with prompt injection, data exfiltration, or credential theft were identified. The instructions guide the agent on how to manage sub-tasks and integrate results without attempting to override system safety constraints.
[SAFE]: No obfuscation techniques, such as Base64 encoding or hidden Unicode characters, are present in the documentation or metadata.

full-send