ClawHub
Back to skill

Security audit

Critical Thinking

Security checks across malware telemetry and agentic risk

Overview

This is a prompt-only critical-thinking workflow; it may make reviews more structured, but it does not run code, access data, or persist anything.

Install this if you want more formal critical-thinking reviews. Be aware it can make responses more structured and evaluative when critique is requested or implied; invoke it explicitly when you want that style, and avoid it for purely creative, wording, or execution-only tasks.

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
90% confidence
Finding
The trigger description is very broad and includes common phrases like 'red team', 'devil's advocate', 'what am I missing', and indirect evaluative language. This can cause unintended activation in ordinary conversations, leading the agent to switch into a rigid review workflow when the user did not explicitly request it, which can override user intent and increase the chance of inappropriate behavior or prompt-routing errors.

VirusTotal

VirusTotal findings are pending for this skill version.

View on VirusTotal

Static analysis

No suspicious patterns detected.