The Agent Skills Directory

[INDIRECT_PROMPT_INJECTION]: The skill is designed to revise prose text provided as input, which creates a potential surface for indirect prompt injection. 1. Ingestion points: The skill processes human-facing text and prose as defined in the SKILL.md description and process sections. 2. Boundary markers: No explicit delimiters or instructions to ignore embedded commands are defined for the input text. 3. Capability inventory: No tools, scripts, network access, or file system operations were detected. The skill configuration explicitly disables model invocation. 4. Sanitization: No input sanitization or filtering logic is present.
[NO_CODE]: The skill consists entirely of instructional markdown and YAML configuration files. No executable Python or Node.js code is provided in the package.

unslop