personal-wellness

Pass

Audited by Gen Agent Trust Hub on Aug 19, 2026

Risk Level: SAFE
Full Analysis
  • [SAFE]: The skill includes comprehensive safety disclaimers and 'When not to use this skill' guidelines, specifically advising users to seek professional medical, psychiatric, or emergency help where appropriate.
  • [SAFE]: The skill uses structured workflows and specialized reference files (references/) to manage different domains of wellness coaching, ensuring consistent and modular behavior.
  • [SAFE]: Tool usage is restricted to specialized MCP tools (sequential-thinking, doc-xlsx) and internal post-processing chains (ai-slop-reviewer, korean-humanize) that are consistent with the vendor's own ecosystem.
  • [SAFE]: No patterns of prompt injection, data exfiltration, obfuscation, or unauthorized privilege escalation were detected in the instructions or reference materials.
  • [SAFE]: The skill appropriately handles sensitive topics like elderly care and parenting by focusing on informational guidance and resource curation rather than providing medical prescriptions.
Audit Metadata
Risk Level
SAFE
Analyzed
Aug 19, 2026, 01:41 PM
Security Audit — agent-trust-hub — personal-wellness