The Agent Skills Directory

[SAFE]: The skill implements a robust security pattern by requiring explicit user confirmation before executing destructive operations. It includes clear instructions to search for specific data, present it to the user, and only proceed with deletion upon receipt of an unambiguous 'yes'.
[SAFE]: No evidence of prompt injection, data exfiltration, or malicious persistence was found. The skill correctly identifies the risk of accidental data loss and provides specific 'Anti-patterns' to prevent automated or unauthorized deletions.
[SAFE]: While the skill interacts with sensitive information (such as memory contents that might include credentials), it does so within the expected scope of a memory management utility and does not transmit this data to any external or unauthorized third-party services.

forget