Dataquant Connector 量化数据通道

• Outcome: Review
• Latest audit: Aug 6, 2026 · 6:44 AM UTC
• Version: 0.1.0

Overview

The skill is a coherent DataQuant market-data connector, but its docs encourage users to paste an API key into chat, which creates avoidable credential exposure.

Install only if you are comfortable giving this skill access to your DataQuant account for market-data queries. Prefer setting DATAQUANT_API_KEY through a local environment variable or a secure secret manager, and avoid pasting real API keys into chat or command history.

SkillSpector

By NVIDIA

Vulnerability Patterns

• Data Exfiltration: External Transmission, Env Variable Harvesting, File System Enumeration
• MCP Least Privilege: Underdeclared Capability, Wildcard Permission, Missing Permission Declaration
• 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 (5)

Lp3

Medium

• Category: MCP Least Privilege
• Confidence: 87% confidence
• Finding: The skill instructs the agent to access environment variables and make outbound network requests, but the skill file does not declare corresponding permissions. This creates a transparency and governance gap: the runtime may still expose secrets or allow network access without the user or platform having an explicit permission record for review.

Missing User Warnings

Medium

• Confidence: 98% confidence
• Finding: The README explicitly instructs users to send their API key directly to the AI assistant in chat, which creates a credential disclosure pattern. In an agent ecosystem, chat content may be logged, retained, forwarded to tools, or exposed in prompt/context handling, making this substantially more dangerous than normal local credential entry.

Missing User Warnings

Medium

• Confidence: 98% confidence
• Finding: The Chinese instructions repeat the same unsafe credential-handling pattern by asking the user to provide the API key directly to the AI. Because this skill is specifically designed for AI-agent use, the context increases risk: secrets entered in conversation may persist in transcripts or be accessible to downstream components.

Ssd 3

Medium

• Confidence: 99% confidence
• Finding: This is a true secret-disclosure issue because the documentation normalizes revealing an API key in plain language to an AI system. In the context of an agent skill, that can lead to credential capture in logs, memory, analytics, debugging traces, or tool invocations, enabling unauthorized API use and account abuse.

Ssd 3

Medium

• Confidence: 99% confidence
• Finding: The Chinese-language example also encourages users to disclose an API key in natural language, which is unsafe by design. Since the skill targets AI assistants, the surrounding context makes accidental credential retention and propagation more likely, increasing the chance of unauthorized access to the DataQuant account.

VirusTotal

VirusTotal findings are pending for this skill version.

Static analysis

No suspicious patterns detected.