coding-agent
Warn
Audited by Snyk on Jul 9, 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: 0.90). The skill repeatedly promotes unsafe execution modes (the --yolo flag “NO sandbox, NO approvals” and an "elevated" run-on-host option) and gives examples using them, which encourages bypassing sandboxing and running agents with host-level access that can modify machine state.
Issues (1)
W013
MEDIUMAttempt to modify system services in skill instructions.
Audit Metadata