The Agent Skills Directory

[SAFE]: No malicious patterns, data exfiltration, or unauthorized command execution were detected in the skill instructions.
[DATA_EXFILTRATION]: The skill manages behavioral profiles and session data but implements explicit privacy tiers (Full, Artifacts-only, Off) and isolation rules (read-write, read-only, deny) to ensure data is not inadvertently synced or leaked across different remotes.
[PROMPT_INJECTION]: The instructions focus on operational logic for compounding knowledge and do not contain commands designed to override safety guidelines or extract system prompts.

learning-loop