Dataify Google Shopping

• Outcome: Pass
• Latest audit: Jun 3, 2026, 8:05 AM
• Version:
  1.0.0

Overview

This is a disclosed Google Shopping helper that sends confirmed search parameters to Dataify, with some usability and credential-handling caveats but no evidence of hidden or malicious behavior.

Install only if you intend to send Google Shopping queries and related filters to Dataify. Review the confirmation table before approving each call, prefer DATAIFY_API_TOKEN over passing tokens on the command line, and be aware that some confirmation labels/descriptions are Chinese-only.

SkillSpector

By NVIDIA

Vulnerability Patterns

• Data Exfiltration: External Transmission, Env Variable Harvesting, File System Enumeration
• Excessive Agency: Unrestricted Tool Access, Autonomous Decision Making, Scope Creep
• 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

Findings (4)

Context-Inappropriate Capability

Medium

• Confidence: 84% confidence
• Finding: The script writes the API token back into process environment state after normalizing it, which expands the token's lifetime and visibility beyond the immediate call path. In agent or plugin runtimes, environment variables may be inherited by child processes, exposed through diagnostics, or unintentionally read by unrelated code, increasing secret exposure risk without necessity for the documented function.

Vague Triggers

Medium

• Confidence: 95% confidence
• Finding: The trigger description is broad enough to activate on common shopping-related requests such as product search or price comparison, which can cause the skill to run in contexts the user did not explicitly intend. Over-broad activation increases the chance of unintended external API use and may route ordinary queries into a third-party data flow without clear user awareness.

Natural-Language Policy Violations

Medium

• Confidence: 88% confidence
• Finding: Forcing a confirmation table with Chinese-only column labels without user opt-in can impair informed consent if the user does not read Chinese. That weakens the safety value of the confirmation step, because users may approve parameters they cannot accurately review.

Natural-Language Policy Violations

Medium

• Confidence: 90% confidence
• Finding: The workflow repeats a requirement for Chinese-only table headers, reinforcing a confirmation UX that may be unreadable to many users. In a flow that gates API execution on user approval, unreadable confirmations undermine meaningful consent and increase the risk of accidental external requests.

VirusTotal

61/61 vendors flagged this skill as clean.