memo
Pass
Audited by Gen Agent Trust Hub on Sep 14, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- Indirect Prompt Injection Surface: The skill is designed to ingest and process external content, including intake summaries and case notes. This creates a potential surface where instructions embedded in these materials could attempt to influence the agent's output. The skill includes specific boundary markers like '[RESEARCH NEEDED]' and '[STUDENT ANALYSIS]' which helps define the scope and maintain user oversight.
- Local Path Access: The skill references specific paths within the user's home directory (e.g., ~/.claude/plugins/config/claude-for-legal/) to determine environment settings like jurisdiction. This is a standard configuration pattern used to scope the legal clinic's practice areas and pedagogical posture.
Audit Metadata