Dataify Google Ai Mode

• Outcome: Review
• Latest audit: Jun 2, 2026, 7:09 AM
• Version:
  1.0.0

Overview

The skill is a coherent Dataify API wrapper, but it deserves review because it can send user queries/location data to a third party and includes an unsafe command-line token pattern.

Install only if you intend to use Dataify for Google AI Mode scraping. Prefer setting DATAIFY_API_TOKEN in the environment instead of pasting tokens into commands or chat, review the confirmation table before each call, and avoid sending sensitive queries or precise location/uule values unless necessary.

SkillSpector

By NVIDIA

Vulnerability Patterns

• Data Exfiltration: External Transmission, Env Variable Harvesting, File System Enumeration
• Trigger Abuse: Overly Broad Trigger, Shadow Command Trigger, Keyword Baiting Trigger
• Prompt Injection: Instruction Override, Hidden Instructions, Exfiltration Commands
• Privilege Escalation: Excessive Permissions, Sudo/Root Execution, Credential Access
• Supply Chain: Unpinned Dependencies, External Script Fetching, Obfuscated Code

Findings (2)

Vague Triggers

Medium

• Confidence: 86% confidence
• Finding: The activation description is broad enough that the skill could trigger for loosely related Google AI searches, causing the agent to route user requests into this skill unexpectedly. Because the skill then guides API form submission and script execution, overbroad activation increases the chance of unintended external requests or inappropriate handling of user queries.

Missing User Warnings

Medium

• Confidence: 85% confidence
• Finding: The script transmits user-supplied search queries and potentially sensitive geographic data such as location or uule to a third-party API endpoint. In a skill context, this can expose private user intent or location-derived metadata without any explicit consent prompt, disclosure, or minimization, creating a data leakage/privacy risk.

VirusTotal

65/65 vendors flagged this skill as clean.