auto-claude-troubleshooting
Warn
Audited by Snyk on Feb 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 prompt includes instructions that request sudo usage (e.g., sudo apt install, sudo npm install -g), suggests bypassing sandbox/security (modify allowlist in security.py or "run without sandbox"), and contains destructive state-changing commands (rm -rf, git branch -D, writing tokens to .env), which together ask the agent to obtain elevated privileges and modify the machine state in ways that can compromise security.
Audit Metadata