The Agent Skills Directory

[COMMAND_EXECUTION]: The skill executes a local script (session_stats.py) using python3 to retrieve recent memory IDs for its 'undo' feature. The script path is scoped to the plugin's local installation directory via platform-provided environment variables.
[INDIRECT_PROMPT_INJECTION]: The skill processes and displays content from a memory database, which constitutes a surface for indirect prompt injection if the stored content contains malicious instructions. The risk is mitigated by an explicit instruction to never delete without human confirmation, preventing automated destructive actions triggered by malicious content.

forget