The Agent Skills Directory

[SAFE]: The skill instructions are strictly focused on linguistic analysis and text transformation. No malicious patterns such as prompt injection, credential harvesting, or obfuscation were identified. The logic includes strong constraints against inventing facts or metadata, ensuring high-fidelity editing.
[EXTERNAL_DOWNLOADS]: The skill includes a reference to a Wikipedia page maintained by WikiProject AI Cleanup. This is a legitimate reference to a well-known external informational resource and does not involve downloading or executing remote code.
[COMMAND_EXECUTION]: The skill is authorized to use Read, Edit, and Write tools to modify user-specified files. This activity is consistent with the skill's primary purpose of editing text and does not involve arbitrary shell command execution, privilege escalation, or persistence mechanisms.

humankit