eu-ai-act

Pass

Audited by Gen Agent Trust Hub on Jul 30, 2026

Risk Level: SAFE
Full Analysis
  • [PROMPT_INJECTION]: The skill establishes a professional persona as a compliance advisor. It does not contain instructions to bypass safety guardrails or disregard system constraints.- [DATA_EXFILTRATION]: No sensitive file access patterns or credential exfiltration attempts were detected. The skill does not perform network requests.- [REMOTE_CODE_EXECUTION]: The skill is comprised of static Markdown files for context and does not download or execute third-party code.- [COMMAND_EXECUTION]: There are no shell commands, system calls, or privilege escalation techniques present in the skill files.- [SAFE]: The skill provides structured educational content focused on Regulation (EU) 2024/1689 and does not expand the agent's technical capabilities or access permissions.
Audit Metadata
Risk Level
SAFE
Analyzed
Jul 30, 2026, 07:33 PM
Security Audit — agent-trust-hub — eu-ai-act