DataHub Unified Data Layer

• Outcome: Pass
• Latest audit: May 28, 2026 at 8:30 AM UTC
• Version:
  1.0.0

Overview

This is a financial data access helper with disclosed external data-source use and no hidden executable payload, though users should be careful with credentials and query privacy.

Install this only if you intend to use DataHub for financial research data retrieval. Treat configured API keys and cookies as sensitive, avoid confidential research queries unless the providers are approved for that use, and prefer local or explicitly chosen sources when privacy matters.

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 (4)

Vague Triggers

Medium

• Confidence: 92% confidence
• Finding: The trigger phrases in the metadata are broad enough to match ordinary user requests like '获取数据' or '查行情', which can cause the skill to activate unexpectedly and route user requests into this skill without clear user intent. In a network-backed skill that fans out to many external data sources, over-activation increases the chance of unnecessary external requests and unintended disclosure of query content.

Vague Triggers

Medium

• Confidence: 94% confidence
• Finding: The 'When to Activate' section uses underspecified conditions such as general requests for financial data, natural-language queries, or building a pipeline, which overlap with many normal assistant tasks. Because this skill is designed to query numerous external services, ambiguous activation logic can cause silent external access when the user may have expected a local or purely conversational response.

Missing User Warnings

Medium

• Confidence: 95% confidence
• Finding: The skill advertises retrieval from 14 data sources and supports natural-language queries, but it does not warn users that their prompts or identifiers may be sent to third-party services. This creates a privacy and transparency risk because users may unknowingly disclose sensitive research interests, securities being analyzed, or other query content to external providers.

Missing User Warnings

Medium

• Confidence: 90% confidence
• Finding: The API key and credential configuration section encourages integration with multiple third-party services, including cookie-based access, without any warning about credential sensitivity, storage, or outbound service access. This can lead to insecure handling of secrets and accidental use of third-party services under the user's credentials without informed consent.

VirusTotal

63/63 vendors flagged this skill as clean.