Draft 1

• Outcome: Pass
• Latest audit: May 28, 2026 at 4:34 AM UTC
• Version:
  1.0.0

Overview

This appears to be a normal drafting helper with a broad trigger, not a skill that runs commands, persists access, or handles sensitive authority.

Install this as a general drafting helper if you are comfortable with it activating on broad writing requests. Review drafts before sending, especially for sensitive business, legal, personal, or credential-related content, and prefer explicit prompts when you want a different skill or no drafting transformation.

SkillSpector

By NVIDIA

Vulnerability Patterns

• Trigger Abuse: Overly Broad Trigger, Shadow Command Trigger, Keyword Baiting Trigger
• Prompt Injection: Instruction Override, Hidden Instructions, Exfiltration Commands
• Data Exfiltration: External Transmission, Env Variable Harvesting, File System Enumeration
• Privilege Escalation: Excessive Permissions, Sudo/Root Execution, Credential Access
• Supply Chain: Unpinned Dependencies, External Script Fetching, Obfuscated Code

Findings (1)

Vague Triggers

High

• Confidence: 89% confidence
• Finding: The trigger description is extremely broad and is designed to activate on many generic writing-related phrases, which can cause the skill to be invoked when the user did not explicitly intend to use it. In an agentic system, unintended invocation can override more appropriate skills, mishandle user intent, or expose user-provided text to a workflow that transforms it in ways the user did not request.

VirusTotal

No VirusTotal findings