ClawHub
Back to skill

Security audit

Dataify Google Search

Security checks across malware telemetry and agentic risk

Overview

This skill is a disclosed Dataify Google Search connector that asks for confirmation before making a scoped API call.

Before installing, understand that the skill sends confirmed search parameters to Dataify using your DATAIFY_API_TOKEN. If you choose to store the token permanently, treat it like any other API secret and avoid pasting it into shared logs or transcripts.

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
95% confidence
Finding
The skill instructs the agent to read environment data for DATAIFY_API_TOKEN, read local reference/script files, and make outbound network requests, but no explicit permissions are declared. This creates a permission-model gap where users and the platform may not have clear visibility or enforcement over sensitive capabilities, increasing the risk of unintended secret access or external data exfiltration if the skill is misused or modified.

VirusTotal

65/65 vendors flagged this skill as clean.

View on VirusTotal

Static analysis

Detected: suspicious.secret_argv_exposure

Instructions pass high-value credentials through process argv.

Critical
Code
suspicious.secret_argv_exposure
Location
SKILL.md:51

Instructions pass high-value credentials through process argv.

Critical
Code
suspicious.secret_argv_exposure
Location
SKILL.zh-CN.md:42