feature-risk-assessment
Pass
Audited by Gen Agent Trust Hub on Jul 3, 2026
Risk Level: SAFE
Full Analysis
- [SAFE]: The skill operates within designated local directories (
~/.claude/plugins/config/claude-for-legal/) for configuration and matter management. These paths are specific to the skill's operational environment and do not involve access to sensitive system directories such as SSH or cloud credentials. - [SAFE]: The 'No silent supplement' and 'Citation check' sections provide strong safeguards against AI hallucinations. They explicitly instruct the agent to stop and report findings if data is thin and require mandatory source attribution (e.g., tagging citations with [Westlaw] or [model knowledge — verify]).
- [SAFE]: The skill uses localized tool commands (e.g.,
/privacy-legal:pia-generation) that are consistent with its stated purpose of coordinating between different legal and governance workflows. - [SAFE]: No obfuscation, prompt injection, or unauthorized network operations were detected in the instructions.
Audit Metadata