The Agent Skills Directory

[SAFE]: The skill consists exclusively of markdown documentation and linguistic guidelines for text editing. No malicious patterns or security risks were identified across any of the files provided.
[NO_CODE]: The skill contains no executable code, scripts, or binary files. Its functionality is implemented entirely through prompt instructions and reference dictionaries, making it inherently low risk from a code execution perspective.
[INDIRECT_PROMPT_INJECTION]: The skill is designed to process user-provided text for rewriting. While this represents a theoretical ingestion point for untrusted data, the skill has no access to sensitive tools, the file system, or the network, meaning any attempts at indirect prompt injection would be confined to the text output and cannot result in data exfiltration or system compromise.

humanizer-tw