feature-risk-assessment
Pass
Audited by Gen Agent Trust Hub on Sep 14, 2026
Risk Level: SAFE
Full Analysis
- File System Interaction: The skill reads from and writes to specific directories located in the user's home directory (
~/.claude/plugins/config/claude-for-legal/). This interaction is used to manage matter-specific context and store decision documents, which is consistent with the skill's purpose as a legal project management tool. - Agent Tool Invocation: The instructions reference calling other specialized commands (e.g.,
/product-legal:matter-workspace,/ai-governance-legal:aia-generation). These are used to transition between different stages of a legal or governance review process. - Content Accuracy Controls: The skill incorporates a 'Citation check' requirement and a 'No silent supplement' policy. These instructions mandate that the agent explicitly tag the source of citations and warn the user that legal research must be verified against primary sources, serving as a safety mechanism against AI hallucinations in a professional context.
Audit Metadata