ClawHub
Back to skill

Security audit

Hardware Inspector

Security checks for vulnerabilities and agentic risk

Overview

This skill clearly performs a read-only hardware inventory, with optional remote inspection only when the user asks for a named SSH host or Kubernetes pod.

Install only if you are comfortable with an agent running local hardware probes and, when explicitly requested, using your existing SSH or kubectl access to inspect a named remote target. Review reports before sharing because redaction is helpful but not perfect.

SkillSpector

Vulnerability Patterns
  • MCP Least PrivilegeUnderdeclared Capability, Wildcard Permission, Missing Permission Declaration
  • 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
Findings (1)

Lp3

Medium
Category
MCP Least Privilege
Confidence
86% confidence
Finding
The skill instructs the agent to execute local Python scripts, write output files, and optionally connect to remote SSH hosts or Kubernetes pods, but the skill declares no permissions despite requiring shell, file read/write, environment access, and network capabilities. This mismatch is dangerous because it can cause the skill to operate with undeclared authority, reducing transparency and making policy enforcement or user consent harder.

Static analysis

No suspicious patterns detected.