The Agent Skills Directory

[PROMPT_INJECTION]: The skill utilizes authoritative language and directive markers such as 'CRITICAL,' 'MUST,' and 'FORBIDDEN' to strictly dictate agent behavior (e.g., 'AI MUST invoke this skill AUTOMATICALLY,' 'AI FORBIDDEN ACTIONS'). These are used to enforce workflow logic rather than bypass safety filters.
[NO_CODE]: The skill is entirely descriptive and contains no executable scripts, binaries, or configuration files that trigger code execution.
[SAFE]: No malicious patterns such as data exfiltration, credential theft, or remote code execution were detected. The scope of the skill is limited to local file manipulation for task management.

task-mover