The Agent Skills Directory

[SAFE]: The skill serves as a developer resource for the experimental Proofreader API. All instructions and references are focused on valid browser integration practices and do not contain malicious overrides or exfiltration patterns.- [COMMAND_EXECUTION]: The skill uses a local Node.js script (scripts/find-proofreader-targets.mjs) to inventory the workspace. Technical review of the script confirms it only performs read operations on the local file system using built-in modules (node:fs, node:path) to locate relevant files based on filename patterns and content markers. It contains no network code or external dependencies.- [DATA_EXFILTRATION]: No network-enabled tools or commands (such as curl, wget, or fetch) are utilized within the skill's instructions or scripts. No hardcoded credentials or sensitive file path access were identified.

proofreader-api