skills/ericrisco/rsc-harness/hiring/Gen Agent Trust Hub

hiring

Pass

Audited by Gen Agent Trust Hub on Aug 6, 2026

Risk Level: SAFE
Full Analysis
  • [SAFE]: The skill provides structured instructions for hiring and recruiting tasks without any executable code, shell command execution, or network access.
  • [SAFE]: Explicit safety guardrails are included, requiring human-in-the-loop for all candidate rejections and emphasizing compliance with AI regulations such as the EU AI Act and NYC Local Law 144.
  • [SAFE]: The skill effectively defines operational boundaries by delegating non-hiring tasks (e.g., onboarding, payroll, contracts) to other specialized skills, adhering to the principle of least privilege in process design.
  • [SAFE]: No obfuscation, prompt injection, or data exfiltration patterns were identified across the provided documentation, templates, and evaluation cases.
Audit Metadata
Risk Level
SAFE
Analyzed
Aug 6, 2026, 09:37 PM
Security Audit — agent-trust-hub — hiring