ClawHub
Back to skill

Security audit

Power Electronics

Security checks across malware telemetry and agentic risk

Overview

This is a disclosed power-electronics helper with local calculation scripts and reference notes; the main caution is broad activation keywords, not malicious behavior.

Installers should be aware that this skill may activate on broad power-electronics terms, including QR, rectification, or inversion. Review the bundled scripts if you plan to run calculations, and only follow the optional publishing/token setup if you are publishing the skill yourself.

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 (4)

Vague Triggers

Medium
Confidence
89% confidence
Finding
The trigger list includes several broad domain terms that can cause the skill to activate on generic power-electronics discussions rather than explicit user intent to use this skill. Unintended invocation can expose tool-enabled behavior (bash/read/write) in contexts where the user did not mean to call the skill, increasing the chance of mis-execution or unnecessary file/tool access.

Overly Broad Trigger

Low
Category
Trigger Abuse
Confidence
86% confidence
Finding
The trigger 'QR' is extremely short and highly ambiguous, so it may match unrelated user inputs such as references to QR codes. This can cause accidental invocation of a tool-enabled skill in irrelevant contexts, creating avoidable exposure to unintended automation.

Overly Broad Trigger

Low
Category
Trigger Abuse
Confidence
82% confidence
Finding
The trigger '整流' is a common technical term that may appear in broad educational or engineering discussions without intent to invoke this particular skill. Because the skill has bash/read/write tools, overly permissive matching increases the risk of accidental activation and unnecessary tool availability.

Overly Broad Trigger

Low
Category
Trigger Abuse
Confidence
82% confidence
Finding
The trigger '逆变' is also a broad, generic term that may occur in many unrelated or high-level discussions. This broad matching can lead to false activations of a skill that exposes execution and file-manipulation tools, which is undesirable even if the content itself is not overtly harmful.

VirusTotal

65/65 vendors flagged this skill as clean.

View on VirusTotal

Static analysis

No suspicious patterns detected.