flywheel
Pass
Audited by Gen Agent Trust Hub on Feb 19, 2026
Risk Level: SAFE
Full Analysis
- Prompt Injection (SAFE): No override or bypass commands were detected in the skill instructions.
- Data Exposure & Exfiltration (SAFE): File access is limited to internal agent data in the .agents/ directory. No network activity or credential harvesting was found.
- Unverifiable Dependencies & Remote Code Execution (SAFE): The skill utilizes the 'ao' CLI but does not download or execute remote scripts or untrusted packages.
- Dynamic Execution (SAFE): No instances of runtime code generation, eval, or unsafe deserialization were identified.
Audit Metadata