apply-anthropic-skill-best-practices
Pass
Audited by Gen Agent Trust Hub on Apr 23, 2026
Risk Level: SAFE
Full Analysis
- [SAFE]: The skill serves as a purely educational resource for authoring AI agent skills. It provides clear guidelines, templates, and concrete examples for structuring instructions and managing complex workflows.
- [COMMAND_EXECUTION]: The guide documents standard patterns for using shell commands and Python scripts (e.g., pdfplumber for PDF extraction or BigQuery for data analysis) within a skill's directory structure. These are presented as educational examples and do not involve the execution of malicious or hidden commands.
- [EXTERNAL_DOWNLOADS]: The skill references images and technical documentation hosted on well-known, official domains (docs.claude.com) and reputable content delivery networks (mintcdn.com) associated with professional documentation platforms. These references are used for instructional purposes and do not trigger unauthorized downloads.
- [DATA_EXPOSURE]: The skill provides a surface for reviewing user-supplied skill content (indicated by the argument-hint), which is its intended primary purpose. It does not perform any unauthorized data access, harvesting, or exfiltration of sensitive files.
Audit Metadata