ClawHub
Back to skill

Security audit

天机我要查 (免费版)

Security checks across malware telemetry and agentic risk

Overview

This skill is a public business-information search helper with disclosed, purpose-aligned web lookup behavior and no evidence of hidden persistence, credential access, exfiltration, or destructive actions.

Before installing, understand that the skill will perform web searches about companies and may optionally run a local baidu-search Python helper if you have configured it. Use it for public business records only, confirm ambiguous company names, and treat results as leads that need official verification rather than professional due diligence advice.

SkillSpector

By NVIDIA
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
88% confidence
Finding
The skill instructs the agent to invoke a local shell command (`python scripts/business_query.py ...`) when certain conditions are met, but the skill declares no permissions for code or shell execution. Even though the command is relatively constrained and the text warns against fabricating results, undeclared execution capability can expand the agent's attack surface and create a permission mismatch that may surprise operators or enable unsafe execution paths.

Vague Triggers

Medium
Confidence
87% confidence
Finding
The README advertises very broad natural-language triggers such as '查一下 XX 公司' and 'XX 有没有被处罚', which are common user phrases and can overlap with ordinary conversation. In an agent environment, this can cause unintentional skill activation on benign mentions of companies or compliance topics, leading to unnecessary web lookups, data aggregation, and context hijacking from the user's primary task.

VirusTotal

64/64 vendors flagged this skill as clean.

View on VirusTotal

Static analysis

No suspicious patterns detected.