outline-builder

Pass

Audited by Gen Agent Trust Hub on Jun 12, 2026

Risk Level: SAFE
Full Analysis
  • [Local Configuration Access]: The skill references a configuration file located at ~/.claude/plugins/config/claude-for-legal/law-student/CLAUDE.md to load user preferences and maintain formatting consistency. This use of a dedicated configuration path is a standard approach for managing tool-specific settings.
  • [Processing of External Materials]: The tool is designed to ingest and format user-provided data such as class notes and casebook excerpts. While ingesting external text represents a common surface for indirect prompt injection, the risk is minimal here as the skill does not possess capabilities for network communication or system command execution.
  • [Strict Behavioral Guidelines]: The instructions include robust 'don't write it for me' rules that prevent the agent from substituting its own knowledge for student synthesis. These constraints serve as a safeguard to ensure the tool remains within its intended educational scope.
Audit Metadata
Risk Level
SAFE
Analyzed
Jun 12, 2026, 08:58 PM
Security Audit — agent-trust-hub — outline-builder