Back to skill

Security audit

Kickbox

Security checks for vulnerabilities and agentic risk

Overview

The artifacts are coherent ClawHub and Convex maintenance skills with disclosed high-impact commands, but no evidence of hidden exfiltration, deception, persistence, or destructive behavior outside their stated purpose.

Install only if you expect ClawHub/Convex maintainer tooling. Be especially careful with the moderation skill and the autoreview helper: use staff tokens only intentionally, review exact commands before writes, and use the documented no-yolo option if you do not want nested Codex review to run with full filesystem authority.

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.