ClawHub
Back to skill

Security audit

blog-polish-eng-single-image

Security checks for vulnerabilities and agentic risk

Overview

The skill bundle is coherent for ClawHub and Convex maintainer workflows, with powerful actions disclosed rather than hidden.

Install this only for ClawHub or Convex development/maintenance contexts. Before running moderation, proof publishing, deployment, or autoreview helper commands, check the target account/repo and command line; use the autoreview --no-yolo option if you do not want nested full-access review.

SkillSpector

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.