ClawHub

Legacy

Security checks across malware telemetry and agentic risk

Overview

This instruction-only skill is not malware, but it asks for or implies access to sensitive financial account data without clear limits or controls.

Install only if you are comfortable with a skill that discusses sensitive financial records. Do not provide bank, brokerage, billing, tax, session, or account credentials to it. Use manually selected, minimal, redacted information, and verify legal, tax, and investment outputs with qualified professionals.

SkillSpector

By NVIDIA
Vulnerability Patterns
  • Trigger AbuseOverly Broad Trigger, Shadow Command Trigger, Keyword Baiting Trigger
  • MCP Tool PoisoningHidden Instructions, Unicode Deception, Parameter Description Injection
  • Prompt InjectionInstruction Override, Hidden Instructions, Exfiltration Commands
  • Data ExfiltrationExternal Transmission, Env Variable Harvesting, File System Enumeration
  • Privilege EscalationExcessive Permissions, Sudo/Root Execution, Credential Access
Findings (3)

Intent-Code Divergence

High
Confidence
97% confidence
Finding
The skill is presented as a family inheritance and legal-planning tool, but the documented capabilities shift into investment analytics, transaction history, statement export, tax details, and near-real-time financial synchronization. This scope mismatch can mislead routing, user consent, and trust boundaries, causing the agent to invoke the skill for sensitive financial operations the user did not reasonably expect from the manifest.

Description-Behavior Mismatch

High
Confidence
96% confidence
Finding
The documented behavior expands materially beyond inheritance/legal guidance into investment tracking, billing exports, tax details, and market-synced account activity. Hidden or under-declared expansion of financial scope is dangerous because it can enable access to highly sensitive financial data and actions under a misleading description, weakening user understanding and platform review controls.

Vague Triggers

Medium
Confidence
85% confidence
Finding
The trigger examples are so generic that they could match many unrelated user requests, increasing the chance the skill is invoked outside its intended context. In a skill touching legal and financial topics, overbroad invocation is more dangerous because it may surface sensitive capabilities or misleading advice when the user did not intend to use this specific tool.

VirusTotal

66/66 vendors flagged this skill as clean.

View on VirusTotal