ClawHub

Google Trends

Security checks across malware telemetry and agentic risk

Overview

This is a straightforward Google Trends helper that makes public Google Trends requests and does not show hidden access, credential use, or destructive behavior.

Install only if you are comfortable with the agent making public web requests to Google Trends and optionally setting up a user-approved daily report. Prefer two-letter country codes and URL-encoded keywords, and avoid passing arbitrary text directly into shell commands.

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
91% confidence
Finding
The skill includes shell-based capabilities and executable script examples using curl, grep, sed, and bash, but does not declare any permissions for shell or network access. This creates a trust and policy gap: an agent or reviewer may assume the skill is non-executing or lower-risk while it actually instructs command execution and outbound requests, increasing the chance of unintended command use or unsafe deployment.

VirusTotal

64/64 vendors flagged this skill as clean.

View on VirusTotal