principle-build-the-lever
Pass
Audited by Gen Agent Trust Hub on Sep 30, 2026
Risk Level: SAFENO_CODE
Full Analysis
- [SAFE]: The skill consists entirely of instructional markdown and configuration files. No executable scripts, binaries, or active code components are included.
- [SAFE]: There are no detected patterns for external downloads, remote code execution, or network requests.
- [SAFE]: The instructions do not contain any prompt injection attempts or efforts to bypass safety guardrails. In fact, the skill recommends security-positive practices such as keeping delegate instructions outside the write scope of subagents to prevent unauthorized modifications.
- [SAFE]: The configuration in agents/openai.yaml explicitly disables implicit invocation, which is a restrictive security setting.
Audit Metadata