ClawHub
Back to skill

Security audit

Site Deployer

Security checks for vulnerabilities and agentic risk

Overview

This is a transparent static-site deployment guide, but users should approve any live production deploy before it runs.

Install only if you want an agent to help create and publish static websites. Before running the deploy example, review the generated files, confirm the target Vercel account/project, and consider removing `--yes` or using a preview deploy first.

SkillSpector

Vulnerability Patterns
  • Data ExfiltrationExternal Transmission, Env Variable Harvesting, File System Enumeration
  • Prompt InjectionInstruction Override, Hidden Instructions, Exfiltration Commands
  • Privilege EscalationExcessive Permissions, Sudo/Root Execution, Credential Access
  • Supply ChainUnpinned Dependencies, External Script Fetching, Obfuscated Code
  • Excessive AgencyUnrestricted Tool Access, Autonomous Decision Making, Scope Creep
Findings (1)

Missing User Warnings

Medium
Confidence
94% confidence
Finding
The skill includes `vercel deploy --prod --yes`, which both publishes to a live production environment and suppresses any interactive confirmation. In an agent skill context, this is risky because an agent may execute the command without surfacing to the user that it is performing an irreversible external action, potentially publishing unintended content or exposing sensitive material.

Static analysis

No suspicious patterns detected.