duck-risk
Pass
Audited by Gen Agent Trust Hub on Oct 13, 2026
Risk Level: SAFE
Full Analysis
- [SAFE]: The skill is a purely instructional framework for performing adversarial risk reviews. It does not contain any executable code, scripts, or command-line instructions.
- [SAFE]: No network operations, external downloads, or remote code execution patterns were detected. All analysis is performed within the agent's context using provided text.
- [SAFE]: The skill explicitly defines safety guardrails in references/GUARDRAILS.md, including "Decision ownership", "Ask-before-act", and "Safety carve-outs" to prevent unauthorized system modifications.
- [SAFE]: No obfuscation, data exfiltration, or persistence mechanisms are present.
Audit Metadata