ClawHub

AIGroup Finnhub MCP

Security checks across malware telemetry and agentic risk

Overview

This skill is a disclosed Finnhub market-data integration whose external MCP use matches its stated finance research purpose.

Install this if you want market-research prompts routed through the aigroup-finnhub-mcp tool. Review and trust the external MCP package before use, prefer pinned versions where possible, and avoid including confidential portfolio, client, or nonpublic business information unless you are comfortable sending it through that tool boundary.

SkillSpector

By NVIDIA
Vulnerability Patterns
  • Trigger AbuseOverly Broad Trigger, Shadow Command Trigger, Keyword Baiting Trigger
  • Prompt InjectionInstruction Override, Hidden Instructions, Exfiltration Commands
  • Data ExfiltrationExternal Transmission, Env Variable Harvesting, File System Enumeration
  • Privilege EscalationExcessive Permissions, Sudo/Root Execution, Credential Access
  • Supply ChainUnpinned Dependencies, External Script Fetching, Obfuscated Code
Findings (2)

Vague Triggers

Medium
Confidence
88% confidence
Finding
The skill’s trigger description is very broad and encourages invocation for a wide range of finance-related requests without stating clear exclusions or decision boundaries. In an agentic setting, this can cause over-routing to the Finnhub MCP, leading to unnecessary external data access, reduced tool-selection precision, and possible leakage of user queries or context to a third-party service when a simpler or offline response would have been sufficient.

Vague Triggers

Medium
Confidence
90% confidence
Finding
The skill enables implicit invocation without defining clear activation constraints, which can cause the agent to call the Finnhub MCP server in ambiguous contexts. Because this tool reaches an external market-intelligence backend over stdio and is broadly described for news, filings, sentiment, and technical analysis, unintended invocation can expose user prompts or trigger unnecessary external actions and data access.

VirusTotal

64/64 vendors flagged this skill as clean.

View on VirusTotal