reference

Pass

Audited by Gen Agent Trust Hub on Jun 21, 2026

Risk Level: SAFE
Full Analysis
  • [SAFE]: The skill establishes a controlled workflow for HR-related document generation, emphasizing factual accuracy and legal compliance.
  • [SAFE]: It implements privacy safeguards, such as requiring explicit consent for salary disclosure and excluding sensitive health or disciplinary records from references.
  • [SAFE]: The skill ingests data from local configuration files (hr.local.md) and user prompts, but lacks any capabilities for network access or code execution, mitigating the risk of data exfiltration or indirect prompt injection.
  • [SAFE]: Mandatory 'REVIEW BEFORE SENDING' headers and jurisdictional context ensure that outputs are handled with appropriate human professional oversight.
Audit Metadata
Risk Level
SAFE
Analyzed
Jun 21, 2026, 09:19 AM
Security Audit — agent-trust-hub — reference