ClawHub
Back to skill

Security audit

Reverse Thinking

Security checks across malware telemetry and agentic risk

Overview

This is a text-only reverse-thinking workflow; its trigger phrases are somewhat broad, but it does not request code execution, credentials, network access, persistence, or hidden high-impact actions.

Install if you want a structured reverse-thinking prompt workflow. Be aware that broad trigger phrases may activate it during ordinary strategy discussions, so prefer invoking it explicitly when you want this style of analysis.

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
88% confidence
Finding
The trigger list includes broad, generic phrases such as '反常识' and '逆向思维' that may appear in ordinary discussion, increasing the chance that the skill is invoked when the user did not explicitly intend to use it. Unintended invocation can steer conversations into this skill’s specialized workflow, causing prompt-routing errors, unexpected behavior, or accidental application of a low-governance reasoning mode in inappropriate contexts.

VirusTotal

63/63 vendors flagged this skill as clean.

View on VirusTotal

Static analysis

No suspicious patterns detected.