Back to skill

Security audit

Agent Security Guard

Security checks for vulnerabilities and agentic risk

Overview

The artifacts describe coherent ClawHub/Convex workflow skills with disclosed admin and migration powers, guarded by user confirmation and existing authenticated tools.

Install only if you expect ClawHub staff, Convex migration, documentation, or code-review workflows. Be careful with the moderation and production-migration skills: they can affect users, packages, emails, or production data when run with valid admin credentials, so review targets and confirmation prompts before allowing writes.

Vulnerability Patterns
  • Prompt InjectionInstruction Override, Hidden Instructions, Exfiltration Commands
  • Data ExfiltrationExternal Transmission, Env Variable Harvesting, File System Enumeration
  • 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

Static analysis

No suspicious patterns detected.