800-policies-eu-ai-act

Pass

Audited by Gen Agent Trust Hub on Jun 13, 2026

Risk Level: SAFE
Full Analysis
  • [SAFE]: The skill is a comprehensive compliance and governance tool that promotes security best practices, such as human-in-the-loop oversight, least privilege, and auditability for AI agents.
  • [EXTERNAL_DOWNLOADS]: The skill references official legal documentation from the European Union law website (eur-lex.europa.eu). This is a well-known, authoritative service for regulatory information.
  • [PROMPT_INJECTION]: The instructions include strict guidelines for a questionnaire workflow, using markers like 'IMPORTANT' and 'MUST' to ensure the AI gathers human input before proceeding. This is a legitimate functional constraint and does not attempt to bypass safety filters.
  • [DATA_EXFILTRATION]: No unauthorized data access or network exfiltration patterns were detected. The skill specifically advises developers to avoid logging sensitive payloads and to implement redaction for RAG systems.
  • [COMMAND_EXECUTION]: There are no executable scripts or shell commands within the skill files. The provided code examples are for educational and architectural guidance purposes.
Audit Metadata
Risk Level
SAFE
Analyzed
Jun 13, 2026, 05:12 AM
Security Audit — agent-trust-hub — 800-policies-eu-ai-act