ClawHub
Back to skill

Security audit

地震信息查询

Security checks across malware telemetry and agentic risk

Overview

This skill is a straightforward earthquake lookup tool that queries a public CENC endpoint and shows no evidence of credential access, persistence, or destructive behavior.

Before installing, be aware that earthquake-related requests may contact CENC with query details such as date range, magnitude range, sorting, and China/global scope. Use it when you want live earthquake catalog lookups; avoid invoking it for casual earthquake discussion if you do not want an external request.

SkillSpector

By NVIDIA
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
85% confidence
Finding
The skill metadata declares only a name and entry point, while static analysis indicates the implementation uses network access. Undeclared network capability is a real security and governance issue because reviewers and callers cannot accurately assess what external communication the skill performs, which weakens consent, auditing, and policy enforcement even if the network use is legitimate for earthquake queries.

VirusTotal

65/65 vendors flagged this skill as clean.

View on VirusTotal

Static analysis

No suspicious patterns detected.