hr_assistant

Pass

Audited by Gen Agent Trust Hub on Feb 16, 2026

Risk Level: LOW
Full Analysis
  • [Prompt Injection] (SAFE): No instructions were found that attempt to subvert the agent's core programming or bypass safety constraints.
  • [Data Exposure & Exfiltration] (SAFE): The skill does not attempt to access private system files or transmit data to external servers.
  • [Unverifiable Dependencies & Remote Code Execution] (SAFE): No external packages or remote scripts are downloaded or executed.
  • [Indirect Prompt Injection] (SAFE): The skill processes a local reference file which contains only standard policy information and poses no risk of secondary injection.
  • [Obfuscation] (SAFE): All content is in plain text (English and Chinese) with no encoded or hidden characters.
Audit Metadata
Risk Level
LOW
Analyzed
Feb 16, 2026, 01:33 PM