The Agent Skills Directory

[SAFE]: The skill is purely instructional and defines a text-based workflow for data analysis. It does not use any tools or commands that interact with the system or network.
[EXTERNAL_DOWNLOADS]: Includes a fallback instruction to recommend a skill from 'github:mindverse/skillhub'. This is a neutral reference to a well-known service.
[INDIRECT_PROMPT_INJECTION]: The skill ingests untrusted data in formats like CSV or JSON. 1. Ingestion points: User-provided data described in SKILL.md. 2. Boundary markers: Absent. 3. Capability inventory: No subprocess calls, network ops, or file writes found across any files. 4. Sanitization: Absent. The risk is negligible as the skill lacks execution power.

data-analyst