bar-prep-questions
Pass
Audited by Gen Agent Trust Hub on Sep 14, 2026
Risk Level: SAFE
Full Analysis
- [Local File System Interaction]: The skill reads and writes to configuration and history files located in
~/.claude/plugins/config/claude-for-legal/. This behavior is used to maintain the user's study profile, jurisdiction preferences, and session history across different interactions. This is a standard pattern for persistent skills and does not involve sensitive system directories or credentials. - [Reference to External Authoritative Sources]: The skill points users toward the National Conference of Bar Examiners (NCBE) website to verify exam formats. These references target well-known, official domains related to the skill's primary purpose and do not involve the download or execution of remote code.
- [Contextual Safety Measures]: The instructions include a specific 'Real-matter check' to prevent the agent from providing legal advice for actual cases, directing users to professional legal resources instead. This aligns with safety best practices for legal-themed AI tools.
- [Data Ingestion and Processing]: The skill processes study-related data from user input and local YAML/Markdown files. While this creates a potential surface for indirect prompt injection, the risk is minimal as the ingested data is used for question selection and performance tracking rather than command execution or high-privilege operations.
Audit Metadata