The Agent Skills Directory

[SAFE]: The skill's instructions are focused entirely on stylistic text editing and do not contain any patterns associated with prompt injection, credential theft, or unauthorized network access.
[INDIRECT_PROMPT_INJECTION]: The skill operates on untrusted text provided by the user or read from local files for style matching, creating a potential surface for indirect instructions.
Ingestion points: Processes text from user prompts and reads from local file paths provided by the user for style reference (SKILL.md).
Boundary markers: The skill does not implement specific delimiters or 'ignore' instructions for the data it processes.
Capability inventory: Includes the ability to Read, Write, Edit, Grep, and Glob files, alongside AskUserQuestion (SKILL.md).
Sanitization: No sanitization or content validation is performed on the input text before the 'humanization' process begins.

humanizer