The Agent Skills Directory

[SAFE]: The skill consists entirely of natural language instructions for text refinement. No executable code, scripts, or external dependencies are included.
[INDIRECT_PROMPT_INJECTION]: The skill is designed to process user-supplied prose, drafts, or documents. This creates a surface for indirect prompt injection where malicious instructions could be embedded in the input text. * Ingestion points: User-provided text or documents identified in the skill description and process instructions. * Boundary markers: The skill does not define specific delimiters (e.g., XML tags or backticks) to isolate the untrusted input from the system instructions. * Capability inventory: The skill's functionality is limited to text rewriting; no tool access (network, file-write, or shell) is defined in the frontmatter or instructions. * Sanitization: No sanitization or validation of the input text is specified.

response-unslop