The Agent Skills Directory

[SAFE]: The skill consists entirely of natural language instructions for text editing and voice adaptation. No malicious patterns or behaviors were detected.
[NO_CODE]: There are no scripts, binaries, or executable commands included in the skill, significantly reducing the attack surface.
[INDIRECT_PROMPT_INJECTION]: The skill is designed to process external prose, which theoretically creates a surface for indirect prompt injection. However, since the skill does not utilize any tools or possess capabilities to interact with the network or file system, this risk is negligible.
Ingestion points: Ingests prose from source material and UI copy (SKILL.md).
Boundary markers: None explicitly defined for input data.
Capability inventory: No subprocess calls, network operations, or file-write capabilities detected.
Sanitization: Standard LLM processing is used; no specific sanitization logic is implemented for the provided text.

writing-voice