coding-agent
Warn
Audited by Snyk on Jul 16, 2026
Risk Level: MEDIUM
Full Analysis
MEDIUM W013: Attempt to modify system services in skill instructions.
- Attempt to modify system services in skill instructions detected (high risk: 1.00). The skill explicitly encourages running agents outside sandboxes and on the host (elevated:true) and documents a “--yolo” no-sandbox/no-approvals mode, which directs the agent to bypass security/isolation and potentially modify host state.
Issues (1)
W013
MEDIUMAttempt to modify system services in skill instructions.
Audit Metadata