The Agent Skills Directory

[SAFE]: The skill is a legitimate text-processing tool. Its instructions focus on identifying and rewriting specific linguistic patterns associated with AI-generated text. It does not perform network operations, access sensitive files, or execute untrusted code.
[DYNAMIC_EXECUTION]: The repository includes a Python script (scripts/validate-package.py) used for development-time validation. This script checks for version consistency and pattern numbering across the skill's files. It only reads local repository files and does not execute during the agent's normal operation of the skill.
[INDIRECT_PROMPT_INJECTION]: The skill processes user-supplied text for rewriting. However, it lacks high-risk capabilities such as network writing, file system modification, or command execution that could be leveraged for an attack. The risk of indirect prompt injection is negligible due to the limited scope of the skill's tools.

humanizer