ai-inventory

Pass

Audited by Gen Agent Trust Hub on Jul 3, 2026

Risk Level: SAFE
Full Analysis
  • [SAFE]: The skill manages its inventory and configuration data using local YAML files located in ~/.claude/plugins/config/claude-for-legal/ai-governance-legal/. This is standard behavior for maintaining persistent state within an agent's workspace.
  • [SAFE]: No prompt injection or behavior override patterns were detected. The skill instructions are focused on providing a structured interview and classification workflow for legal compliance.
  • [SAFE]: No network operations or external data exfiltration patterns were identified. The skill does not use tools like curl, wget, or any external APIs.
  • [SAFE]: The classification logic for the EU AI Act is implemented as a transparent walk-through, requiring user confirmation and including explicit 'verify' tags to ensure human oversight.
Audit Metadata
Risk Level
SAFE
Analyzed
Jul 3, 2026, 03:57 PM
Security Audit — agent-trust-hub — ai-inventory