The Agent Skills Directory

[NO_CODE]: The skill consists entirely of markdown instructions and YAML configuration settings. No executable scripts, binaries, or external code dependencies are included.
[PROMPT_INJECTION]: The skill exhibits a potential surface for indirect prompt injection (Category 8) due to how it handles untrusted data.
Ingestion points: The skill is designed to ingest and transform arbitrary text provided by the user or read from external files.
Boundary markers: The instructions lack explicit delimiters or "ignore instructions" warnings to separate the content being edited from the agent's core instructions.
Capability inventory: The skill is authorized to use Read, Write, and Edit tools to modify the user's workspace based on the processed text.
Sanitization: There is no logic provided to sanitize or validate the input text for embedded malicious commands before the agent processes it.

humanizer-zh