status

Pass

Audited by Gen Agent Trust Hub on Jul 3, 2026

Risk Level: SAFE
Full Analysis
  • [DATA_EXPOSURE]: The skill accesses a configuration file at ~/.claude/plugins/config/claude-for-legal/legal-clinic/CLAUDE.md. This is used to retrieve supervision styles, plain-language standards, and jurisdictional context, which is consistent with the skill's stated purpose for a legal clinic environment.
  • [PROMPT_INJECTION]: No malicious prompt injection patterns or instructions to bypass safety guidelines were detected. The skill actually emphasizes following professional guidelines and attorney supervision.
  • [COMMAND_EXECUTION]: No shell commands or dangerous script executions were identified.
  • [EXTERNAL_DOWNLOADS]: No external network requests or remote code downloads were found.
  • [SAFE]: The skill implements best practices for its domain, including clear markers for AI-assisted drafts ([AI-ASSISTED DRAFT]) and reminders that court filings and client communications require human attorney review.
Audit Metadata
Risk Level
SAFE
Analyzed
Jul 3, 2026, 03:58 PM
Security Audit — agent-trust-hub — status