Self Improving Skill

• Outcome: Pass
• Latest audit: Jun 10, 2026 at 6:51 AM UTC
• Version:
  1.0.1

Overview

The available evidence shows a self-improvement skill with a broad activation trigger, but no signs of malware, hidden persistence, credential use, exfiltration, or destructive behavior.

This looks acceptable to install if you want a self-improvement or study-planning helper. Review the trigger wording before publishing or relying on it in a multi-skill environment, because generic phrases may cause it to activate when the user only wanted ordinary advice.

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: 89% confidence
• Finding: The trigger phrases are broad enough to match ordinary user requests like asking how to improve or requesting a plan, which can cause the skill to activate outside the user's intended context. That increases the chance of prompt hijacking or unintentional routing, especially in environments where multiple skills compete for similar natural-language inputs.

VirusTotal

53/53 vendors flagged this skill as clean.