ClawHub
Back to skill

Security audit

Dataify Google Trends

Security checks for vulnerabilities and agentic risk

Overview

The skill is a straightforward Google Trends helper that sends user-selected trend queries to Dataify with an API token, and I found no hidden persistence, destructive behavior, or unrelated data access.

Install this only if you are comfortable sending Google Trends query terms, filters, and your Dataify API token to Dataify. Configure the token through the environment rather than chat, and make sure your agent uses the skill for Google Trends data, not general web search.

SkillSpector

Vulnerability Patterns
  • Data ExfiltrationExternal Transmission, Env Variable Harvesting, File System Enumeration
  • 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
  • Privilege EscalationExcessive Permissions, Sudo/Root Execution, Credential Access
Findings (3)

Lp3

Medium
Category
MCP Least Privilege
Confidence
92% confidence
Finding
The skill instructs the agent to read environment state, run a local script, and make networked API requests, but no declared permissions are present. That mismatch weakens review and policy enforcement because operators may not realize the skill can access credentials and perform outbound calls.

Missing User Warnings

Medium
Confidence
82% confidence
Finding
The skill instructs the agent to run a Python script that submits user-derived parameters to an external Dataify API, but the top-level description does not clearly warn that this causes outbound network transmission. In an agent setting, inadequate disclosure can lead users to reveal sensitive queries or assume a local-only operation when their data is actually sent to a third party.

Vague Triggers

Medium
Confidence
80% confidence
Finding
The default prompt uses a very generic invocation instruction, 'Use $dataify-google-trends to run a search query,' without constraining that the tool should only be used for Google Trends data. This can cause an agent or user to invoke the skill for broader search-like tasks than intended, increasing the chance of misuse, policy bypass, or incorrect delegation.

Static analysis

No suspicious patterns detected.