first skill

• Outcome: Pass
• Latest audit: May 28, 2026 at 6:28 AM UTC
• Version:
  1.0.1

Overview

This appears to be a normal skill-authoring helper that creates and validates local skill folders, with no confirmed hidden or destructive behavior.

Install only if you want an agent to help create or update local skills. Before approving commands, check the skill name and output directory, avoid untrusted path fragments, and review generated skill files before enabling or sharing them.

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 (2)

Vague Triggers

Medium

• Confidence: 85% confidence
• Finding: The trigger description is very broad and can activate on generic phrases like 'new skill' or 'skill for X', which risks unintended invocation in contexts unrelated to repository modification. Over-broad activation is dangerous because this skill guides file creation, editing, and script execution, so accidental triggering can lead to unnecessary writes or workflow hijacking.

Missing User Warnings

Low

• Confidence: 80% confidence
• Finding: The instructions tell the agent to run initialization and validation scripts without clearly warning that initialization creates directories and files and validation may inspect local paths. In an agent setting, omitting side-effect warnings increases the chance of unexpected filesystem modification without informed user confirmation.

VirusTotal

64/64 vendors flagged this skill as clean.