Skill Builder
Pass
Audited by Gen Agent Trust Hub on Feb 17, 2026
Risk Level: SAFENO_CODE
Full Analysis
- [Prompt Injection] (SAFE): The instructions are purely focused on providing a framework for creating other skills. No bypass markers, role-play injections, or instructions to ignore previous constraints were found.
- [Data Exposure & Exfiltration] (SAFE): No sensitive file paths (e.g., SSH keys, cloud credentials) or network-related commands (curl, wget) are present. There are no hardcoded secrets or API keys.
- [Remote Code Execution] (SAFE): The skill does not reference or download any external scripts, binaries, or packages. It is entirely composed of Markdown text.
- [Privilege Escalation & Persistence] (SAFE): There are no commands related to system modification, privilege escalation (sudo), or persistence (crontab, shell profiles).
- [Dynamic Execution] (SAFE): No dynamic code generation or unsafe deserialization patterns are present.
Audit Metadata