ClawHub
Back to skill

Security audit

电商导购助手

Security checks for vulnerabilities and agentic risk

Overview

The skill artifacts are coherent helper workflows for ClawHub and Convex development, with the higher-impact actions described and tied to explicit user-driven tasks.

Install only if you expect ClawHub/Convex maintainer workflows. Review the moderation and autoreview sections before use: moderation commands can affect users or public content, and autoreview may run high-privilege local review commands or share diffs with configured fallback reviewers.

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.