vercel-deploy

CRITICAL E006: Malicious code pattern detected in skill scripts.

• Malicious code pattern detected (high risk: 1.00). The repository includes a deployment script that packages and uploads a user's project to a hard-coded external endpoint and the skill instructs escalating network permissions, constituting high-risk data exfiltration and potential abuse of sandbox/network escalation.

MEDIUM W013: Attempt to modify system services in skill instructions.

• Attempt to modify system services in skill instructions detected (high risk: 0.80). The skill explicitly instructs the agent to rerun the deploy command with "escalated" sandbox permissions (sandbox_permissions=require_escalated) to bypass sandboxed networking, which requests bypassing security mechanisms even though it does not ask for sudo, system-file changes, or user creation.