outline-builder

Pass

Audited by Gen Agent Trust Hub on Jul 25, 2026

Risk Level: SAFE
Full Analysis
  • [Contextual File Access]: The skill is designed to access a configuration file at ~/.claude/plugins/config/claude-for-legal/law-student/CLAUDE.md to load student preferences and maintain outline consistency. While accessing local configuration paths is a security consideration, this is used within the skill to provide a tailored and consistent user experience for legal education workflows.
  • [Data Ingestion Surface]: The skill processes information from external sources provided by the user, such as casebooks, syllabuses, and class notes. This creates a potential surface for indirect prompt injection if the ingested materials contain unexpected instructions. The skill mitigates this by implementing a strict "don't write it for me" rule, ensuring that substantive content remains driven by the user and clearly marking any information that requires further verification.
Audit Metadata
Risk Level
SAFE
Analyzed
Jul 25, 2026, 12:36 AM
Security Audit — agent-trust-hub — outline-builder