The Agent Skills Directory

[SAFE] (SAFE): The skill consists of markdown documentation and code examples intended to guide developers in creating CLI tools. No evidence of prompt injection, data exfiltration, or unauthorized command execution was found.
[COMMAND_EXECUTION] (LOW): The skill includes shell script examples involving kubectl for managing deployments. These are presented as architectural patterns for 'Safe Automation with Rollbacks' rather than instructions for the agent to execute immediately. The use of temporary files (/tmp/rollback-$$.yaml) follows standard practices for session-based backups.

command-patterns