ClawHub
Back to skill

Security audit

具身智能前沿追踪系统

Security checks for vulnerabilities and agentic risk

Overview

The skill is a normal-looking embodied-AI research digest, but it asks for broad shell and local file access that is not clearly needed for public web research.

Review before installing. The research workflow itself is coherent, but users should prefer running it with web/search-only permissions or require confirmation for any shell command or local file access.

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.