The Agent Skills Directory

[SAFE]: The skill implements logic for managing user preferences using internal memory systems. No malicious behaviors or executable scripts were found in the skill content.
[DATA_EXFILTRATION]: The skill uses memory read and write permissions to persist user preferences. It does not perform network operations, access sensitive file paths, or attempt to exfiltrate data to external servers.
[PROMPT_INJECTION]: The instructions are focused on learning user preferences and do not contain attempts to override safety filters, bypass system constraints, or hijack agent behavior.

preference-learner