ClawHub
Back to skill

Security audit

Claude给中国用户的"标记"扫描器

Security checks for vulnerabilities and agentic risk

Overview

The skill appears to be a Claude Code maintenance helper, with review-worthy but disclosed local command and upgrade behavior rather than evidence of malware or deception.

Install only if you want an agent to inspect or maintain your local Claude Code setup. Before approving commands, confirm they are limited to version checks or the intended Claude Code package upgrade, especially because global npm changes persist outside the current session.

SkillSpector

Vulnerability Patterns
  • Trigger AbuseOverly Broad Trigger, Shadow Command Trigger, Keyword Baiting Trigger
  • 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
Findings (2)

Lp3

Medium
Category
MCP Least Privilege
Confidence
91% confidence
Finding
The skill instructs the agent to run local shell commands and perform a global package upgrade, but it does not declare permissions or otherwise constrain that capability. This creates a real security and safety issue because users or orchestrators may not realize the skill can execute commands that inspect the local system and modify globally installed software.

Vague Triggers

Medium
Confidence
85% confidence
Finding
The trigger list contains broad phrases such as cleanup, upgrade, and Unicode/date prompt checks that may match ordinary support or troubleshooting requests. Overbroad activation increases the chance the skill is invoked unexpectedly, which is more concerning here because the workflow includes shell execution and a global npm upgrade path.

Static analysis

No suspicious patterns detected.