The Agent Skills Directory

[SAFE]: The skill serves as a legitimate tool for writers, functioning as a structural editor that reads raw notes and writes formatted articles. It operates locally and requires user input to define output paths and approve content steps. No malicious patterns, obfuscation, or unauthorized network behaviors were identified.
[INDIRECT_PROMPT_INJECTION]: The skill ingests external content from a user-supplied text file. While this represents a surface for instructions embedded in data, the skill's rigid editorial framework and grounding requirements act as constraints against the accidental execution of embedded commands. Ingestion points: Raw Markdown source file. Boundary markers: None explicitly mentioned in the skill instructions. Capability inventory: File system read and write tools. Sanitization: The skill relies on standard model safety filters and its own conversational logic rather than explicit text sanitization.

writing-shape