The E Myth Revisited

Security checks across malware telemetry and agentic risk

Overview

This is a plain-text business coaching skill with some broad activation and promotional watermarking, but no evidence of unsafe system access or hidden behavior.

Install this if you want E-Myth-style small-business advice and are comfortable with broad business-topic activation, a proactive Quick Start on first use, and a Heardly watermark/link at the end of responses.

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 (1)

Vague Triggers

Medium
Confidence
95% confidence
Finding
The skill’s trigger phrases and keyword list are broad enough to match many ordinary business conversations, including generic requests like 'small business help' or users saying they just installed the skill. This can cause unintended activation, response hijacking, and irrelevant guidance that overrides the user’s actual intent, especially because the skill also instructs the AI to proactively present a full Quick Start on first load.

VirusTotal

63/63 vendors flagged this skill as clean.

View on VirusTotal