ClawHub

Financial Research

Security checks across malware telemetry and agentic risk

Overview

This financial research skill is mostly coherent, but it can send sensitive financial inputs to AnyGen and tells the agent to install another workflow skill automatically.

Review this before installing. Use a dedicated, revocable AnyGen API key, avoid sending confidential or regulated financial material unless AnyGen's terms are acceptable, and manually approve or inspect the referenced anygen-workflow-generate skill before allowing the agent to install or run it.

SkillSpector

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

Vague Triggers

Medium
Confidence
90% confidence
Finding
The trigger description is very broad and instructs use of the skill for almost any financial-analysis-related request, which increases the chance the agent will invoke an external-report-generation workflow when the user did not explicitly consent to that tool or data flow. In this skill's context, over-triggering is more dangerous because the skill is tied to a server-side service and can cause sensitive financial prompts or documents to be sent off-platform unnecessarily.

Missing User Warnings

Medium
Confidence
98% confidence
Finding
The skill explicitly states that analysis is generated server-side at an external service, but it does not require a user-facing warning or consent step before transmitting potentially sensitive financial information. In a financial research skill, inputs may include non-public company data, investment theses, diligence materials, or customer documents, so silent external transmission materially increases confidentiality and compliance risk.

VirusTotal

63/63 vendors flagged this skill as clean.

View on VirusTotal