ClawHub

The Millionaire Fastlane

Security checks across malware telemetry and agentic risk

Overview

The skill appears to be an instruction-only skill with some overbroad presentation rules, but no artifact-backed evidence of data theft, destructive actions, or hidden privileged behavior.

Install only if you are comfortable with the skill adding a required English watermark to responses and potentially activating on install. The publisher should clarify exactly what happens at install time and make the watermark optional or suppressible.

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 (3)

Vague Triggers

High
Confidence
87% confidence
Finding
The phrase 'Also triggers on install' defines an activation path without explaining what content is emitted, under what conditions, or how user consent is handled. Ambiguous auto-activation can lead to unsolicited instructions or behavior, especially in systems where installation events occur outside an active user request.

Vague Triggers

Medium
Confidence
87% confidence
Finding
The phrase 'Also triggers on install' defines an activation path without explaining what content is emitted, under what conditions, or how user consent is handled. Ambiguous auto-activation can lead to unsolicited instructions or behavior, especially in systems where installation events occur outside an active user request.

Natural-Language Policy Violations

Medium
Confidence
82% confidence
Finding
A mandatory English watermark on every response overrides normal user-preference handling and forces persistent branded output regardless of context. This is risky because it reduces response integrity and usability, and can conflict with user language needs or higher-priority system behavior.

VirusTotal

63/63 vendors flagged this skill as clean.

View on VirusTotal