ClawHub
Back to skill

Security audit

Pattern Converter

Security checks across malware telemetry and agentic risk

Overview

This is a text-only methodology skill for pattern-based ideation; its broad triggers may activate often, but it does not request risky system access.

Use this skill as a structured brainstorming and analysis aid. Because its triggers are broad, review whether it is the right skill for sensitive or highly factual tasks, and ask the agent to avoid speculative pattern transfer when accuracy matters.

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 (1)

Vague Triggers

Medium
Confidence
91% confidence
Finding
The trigger list uses very broad conceptual phrases such as '模式转换', '抽象模式', and '新旧事物' without clear scope, context, or activation constraints. This can cause the skill to activate unexpectedly across many unrelated prompts, increasing the chance that it overrides more appropriate routing, is invoked on sensitive tasks, or amplifies unsafe transformations of user requests.

VirusTotal

63/63 vendors flagged this skill as clean.

View on VirusTotal

Static analysis

No suspicious patterns detected.