The Agent Skills Directory

[SAFE]: The repository consists entirely of Markdown documentation and prompt instructions. No binary files, executable scripts, or hidden code blocks were found across the analyzed files.
[COMMAND_EXECUTION]: The skill configuration lists standard file-system operations (Read, Write, Edit, Grep, Glob) in the allowed-tools section. These tools are restricted by the platform and are appropriate for the skill's intended purpose of analyzing and editing text documents.
[EXTERNAL_DOWNLOADS]: The documentation provides standard installation instructions using git clone. This is a user-initiated action for deployment and does not constitute a runtime vulnerability or remote code execution pattern.
[PROMPT_INJECTION]: The instructions provided to the agent focus on text transformation and quality assurance. There are no attempts to bypass safety filters, escalate privileges, or extract sensitive system information.
[DATA_EXFILTRATION]: No network-based tools or instructions to transmit data to external domains are present. The skill operates locally on the text provided by the user.

humanizer