The Art Of Deception Controlling The Human Element Of Security

• Outcome: Pass
• Latest audit: Jun 13, 2026 at 11:54 AM UTC
• Version:
  1.0.0

Overview

The available evidence shows no malware or harmful actions, but the full skill artifact was not present to verify beyond scanner telemetry.

Install only if you are comfortable with the skill appearing in broad security- or hacking-related conversations. Treat it as educational content, and review its actual SKILL.md before use if you want tighter trigger behavior.

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

Medium

• Confidence: 95% confidence
• Finding: The skill is configured to trigger on extremely broad terms such as 'security', 'hacking', 'phishing', and even on users saying they just installed the skill. This can cause the skill to activate in many unrelated contexts, increasing the chance of unwanted interception, response hijacking, or accidental exposure of users to social-engineering-themed content when they did not explicitly request it.

VirusTotal

64/64 vendors flagged this skill as clean.