同花顺问财ETF选股

• Outcome: Pass
• Latest audit: May 29, 2026 at 8:36 PM UTC
• Version:
  1.0.0

Overview

This is a coherent ETF screening skill that uses a disclosed third-party IWENCAI market-data API, with privacy and scope caveats but no evidence of hidden, destructive, or deceptive behavior.

Install only if you are comfortable sending ETF screening queries to the IWENCAI service using your API token. Avoid including private portfolio details, account information, or proprietary investment strategy in queries, and keep any extra search or financial-tool use explicit and limited to the ETF research task.

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
• MCP Least Privilege: Underdeclared Capability, Wildcard Permission, Missing Permission Declaration
• MCP Tool Poisoning: Hidden Instructions, Unicode Deception, Parameter Description Injection
• Prompt Injection: Instruction Override, Hidden Instructions, Exfiltration Commands

Findings (5)

Lp3

Medium

• Category: MCP Least Privilege
• Confidence: 90% confidence
• Finding: The skill documents use of environment variables and outbound network access, but no explicit permissions or user-facing disclosure are declared. This creates a transparency and governance gap: a caller may invoke the skill expecting simple local ETF filtering while the skill can access secrets and send queries to an external service.

Tp4

High

• Category: MCP Tool Poisoning
• Confidence: 88% confidence
• Finding: The skill is described as an ETF screening tool, but its documented behavior accepts arbitrary natural-language queries and forwards them to a general remote query API using a Bearer token. This mismatch can cause over-broad data transmission, user surprise, and misuse beyond the narrowly declared ETF-screening scope.

Context-Inappropriate Capability

Medium

• Confidence: 84% confidence
• Finding: The documentation permits the skill to call other financial or search tools when it decides more context is needed, which expands data flow and capabilities beyond the stated ETF-screening purpose. That increases the attack surface and may expose user prompts or derived financial interests to additional external services without clear consent.

Missing User Warnings

Medium

• Confidence: 93% confidence
• Finding: The skill explicitly documents sending queries over the network with an API key, but does not warn users that their input will be transmitted to a third-party service. For financial queries, this can expose potentially sensitive investment interests, strategies, or proprietary research prompts to an external provider.

Missing User Warnings

Medium

• Confidence: 84% confidence
• Finding: The documentation explicitly instructs the agent to send the user's natural-language query directly to an external API and notes API-key authentication, but provides no user-facing disclosure, consent, or guidance on handling sensitive content. This creates a real privacy and data-governance risk because users may unknowingly transmit personal or confidential financial queries to a third-party service.

VirusTotal

67/67 vendors flagged this skill as clean.