conversation-professional-b2b

Pass

Audited by Gen Agent Trust Hub on Jun 22, 2026

Risk Level: SAFE
Full Analysis
  • [SAFE]: The skill is a set of natural language instructions designed to modify the AI's persona, formatting, and citation style for a specific professional audience.
  • [EXTERNAL_DOWNLOADS]: The skill metadata references a source repository at github.com/sboghossian/mini-claude-for-legal. This is a static reference for attribution and does not involve automated downloads or runtime execution of remote scripts.
  • [PROMPT_INJECTION]: The instructions include directives to suppress consumer-oriented disclaimers when the audience is identified as professional. These instructions are context-aware, defer to existing platform refusal policies, and are intended for persona consistency rather than bypassing safety guardrails.
Audit Metadata
Risk Level
SAFE
Analyzed
Jun 22, 2026, 02:24 PM
Security Audit — agent-trust-hub — conversation-professional-b2b