ClawHub
Back to skill

Security audit

Dataify Google AI Mode

Security checks for vulnerabilities and agentic risk

Overview

This skill does what it says: it sends explicit Google AI Mode searches to Dataify using a Dataify token, with no hidden persistence or unrelated data access found.

Before installing, be comfortable sending your search query and selected location/language/output parameters to Dataify and using Dataify API credits. Configure the token as an environment variable and avoid command-line token arguments or permanent shell-profile changes unless you understand the exposure tradeoff.

SkillSpector

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
88% confidence
Finding
The skill instructs the agent to read an environment variable, execute a bundled Python script, and make outbound API requests, but the skill file does not declare corresponding permissions. This mismatch can bypass expected user or platform scrutiny, making the skill more dangerous because it can access credentials and the network despite appearing minimally scoped.

Static analysis

No suspicious patterns detected.