shared-kernel
Pass
Audited by Gen Agent Trust Hub on Feb 17, 2026
Risk Level: SAFENO_CODE
Full Analysis
- Prompt Injection (SAFE): The content consists entirely of architectural documentation and coding standards. There are no instructions aimed at overriding agent behavior or bypassing safety filters.
- Data Exposure & Exfiltration (SAFE): No hardcoded credentials, secrets, or references to sensitive local files were found. There are no network-related commands.
- Remote Code Execution & Dependencies (SAFE): The skill does not include any scripts, package manifests, or commands to download or execute remote content.
- Persistence & Privilege Escalation (SAFE): No commands for system modification, privilege elevation, or maintaining persistence are present.
Audit Metadata