The Agent Skills Directory

[SAFE]: The skill is designed for copy editing and typographic review. It operates by processing user-provided text and returning feedback within the chat interface. It does not utilize any tools, perform network requests, or access the local file system.- [PROMPT_INJECTION]: The instructions establish a clear persona ('ruthless but fair copy editor') focused on specific writing principles (Orwellian rules and typography). No instructions were found that attempt to bypass AI safety guidelines, extract system prompts, or disregard platform constraints.- [DATA_EXFILTRATION]: There is no evidence of network operations, credential harvesting, or access to sensitive local files (such as SSH keys or environment variables). All data processing occurs locally within the conversation context.- [REMOTE_CODE_EXECUTION]: The skill contains no patterns for downloading external scripts, installing third-party packages, or executing remote code.- [COMMAND_EXECUTION]: No shell commands, subprocess calls, or dynamic execution patterns (like eval or exec) were detected in the instructions.

red-pen