ClawHub
Back to skill

Security audit

Dataify Google Lens

Security checks for vulnerabilities and agentic risk

Overview

This skill is a disclosed Dataify Google Lens integration that sends user-provided image search parameters to Dataify, with no hidden persistence or unrelated data access found.

Install only if you are comfortable sending the image URL, optional query text, and search parameters to Dataify for processing. Avoid using private, internal, signed, or sensitive image URLs unless you have confirmed that this third-party API handling is acceptable.

SkillSpector

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 (3)

Lp3

Medium
Category
MCP Least Privilege
Confidence
93% confidence
Finding
The skill instructs the agent to read environment variables, invoke a local Python script, and make outbound network requests, yet no declared permissions are present. This creates a governance and transparency gap: an agent may perform sensitive actions without an explicit permission model, making unintended secret access or network exfiltration harder to detect or constrain.

Missing User Warnings

Medium
Confidence
91% confidence
Finding
The reference directs the agent to show parameters before sending a request, but it never instructs the agent to warn the user that the provided image URL will be transmitted to Dataify, a third-party service. That omission can cause unintentional disclosure of sensitive URLs or private image locations, especially if users assume analysis is performed locally or only by Google Lens rather than an intermediary API.

Missing User Warnings

Medium
Confidence
88% confidence
Finding
The script sends user-supplied image URLs and optional query text to a third-party API, which can disclose sensitive browsing targets, internal resource URLs, or private investigation context without an explicit warning or consent step. In an agent-skill context, this is more dangerous because users may assume local processing while the tool actually exfiltrates inputs off-platform.

Static analysis

No suspicious patterns detected.