worker-classification

Pass

Audited by Gen Agent Trust Hub on May 13, 2026

Risk Level: SAFE
Full Analysis
  • [Structured Intake and Fact Processing]: The skill functions by ingesting user-provided descriptions of working arrangements. This information is used as the basis for legal analysis. While processing untrusted user data is an essential part of the skill's utility, it represents the primary surface where external content enters the agent's context.
  • [Scoped File System Interaction]: The skill manages matter-specific data and jurisdictional configurations by reading from and writing to specific directories within the plugin's workspace (~/.claude/plugins/config/claude-for-legal/). These operations are scoped to the tool's own configuration and matter-management environment.
  • [Legal Research Integration]: To apply accurate legal tests, the skill is designed to interface with external research tools such as Westlaw or CourtListener. This connectivity is a functional requirement that allows the agent to base its analysis on currently operative statutes and case law rather than static training data.
Audit Metadata
Risk Level
SAFE
Analyzed
May 13, 2026, 12:40 AM