ClawHub
Back to skill

Security audit

锋哥 Bing 搜索

Security checks across malware telemetry and agentic risk

Overview

This is a straightforward Bing search helper that sends search terms to Bing and does not show hidden credential, persistence, or system-modifying behavior.

Install only if you are comfortable with your search terms being sent to Bing. Avoid searching secrets, private project names, or sensitive internal text, and be aware that scraping Bing HTML may be brittle or subject to provider terms.

SkillSpector

By NVIDIA
Vulnerability Patterns
  • Data ExfiltrationExternal Transmission, Env Variable Harvesting, File System Enumeration
  • MCP Least PrivilegeUnderdeclared Capability, Wildcard Permission, Missing Permission Declaration
  • Prompt InjectionInstruction Override, Hidden Instructions, Exfiltration Commands
  • Privilege EscalationExcessive Permissions, Sudo/Root Execution, Credential Access
  • Supply ChainUnpinned Dependencies, External Script Fetching, Obfuscated Code
Findings (2)

Lp3

Medium
Category
MCP Least Privilege
Confidence
94% confidence
Finding
The skill advertises and requires network-capable components ('python3' and 'requests') and its purpose is to perform live Bing searches, but the manifest shown does not declare any explicit network permission. Undeclared network access weakens the trust boundary for users and platforms because the skill can send user queries to external services without transparent permission gating or policy review.

Missing User Warnings

Low
Confidence
86% confidence
Finding
The skill sends the user's raw search query to Bing, which can expose sensitive prompts, internal project names, credentials pasted by mistake, or other private data to a third party. In an agent context, this is more dangerous because users may assume local tool execution and may not realize their input is being transmitted externally.

VirusTotal

65/65 vendors flagged this skill as clean.

View on VirusTotal