agent-builder
Pass
Audited by Gen Agent Trust Hub on Mar 1, 2026
Risk Level: SAFENO_CODE
Full Analysis
- [SAFE]: The skill consists exclusively of markdown documentation and templates. No executable scripts, binaries, or active code components are included in the package.
- [PROMPT_INJECTION]: The instructional content is focused on defining agent boundaries and safety protocols. There are no patterns identified that attempt to bypass, override, or ignore the AI's safety guidelines.
- [DATA_EXFILTRATION]: No network operations or sensitive file system access patterns were detected. The skill specifically instructs users and agents not to store credentials or secrets within the workspace files.
- [REMOTE_CODE_EXECUTION]: There are no mechanisms present for downloading or executing remote code or packages from external sources.
- [CREDENTIALS_UNSAFE]: No hardcoded API keys, passwords, or sensitive tokens were found within the skill files or templates.
Audit Metadata