onboarding-new-hires
Pass
Audited by Gen Agent Trust Hub on Feb 19, 2026
Risk Level: SAFE
Full Analysis
- Prompt Injection (SAFE): No instructions designed to bypass AI safety filters or override system behavior were found.
- Data Exposure & Exfiltration (SAFE): The skill does not access sensitive files or hardcode credentials. It includes explicit guidance for users to redact sensitive info and avoid secrets.
- Unverifiable Dependencies & Remote Code Execution (SAFE): There are no scripts, package files, or commands that download or execute external code.
- Indirect Prompt Injection (SAFE): While the skill processes user-supplied context, it possesses no dangerous capabilities such as file writing or network access that could be exploited via malicious input.
Audit Metadata