The Agent Skills Directory

[PROMPT_INJECTION]: The skill contains a section titled 'CRITICAL: Auto-start on load' which instructs the agent to bypass summarization and preamble. While this uses forceful language to control agent behavior, it is limited to the specific task of streamlining output for the user's requested hooks and does not attempt to bypass safety filters or extract system information.
[DATA_EXFILTRATION]: No network operations, credential harvesting, or sensitive file access patterns were detected. The skill operates entirely within the text generation context.
[REMOTE_CODE_EXECUTION]: There are no commands to download or execute external scripts, and no dependencies are specified.
[COMMAND_EXECUTION]: The skill does not invoke any shell commands or system-level tools.

hook-generator