ClawHub
Back to skill

Security audit

Random Driven

Security checks across malware telemetry and agentic risk

Overview

This is a text-only creative brainstorming skill with no executable code, credentials, network access, or persistence behavior.

Install only if you want an agent to use random-association brainstorming patterns. Invoke it intentionally for creative ideation, and avoid relying on it for factual, legal, medical, financial, or operational decisions without separate verification.

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
89% confidence
Finding
The skill advertises broad trigger phrases such as '随机性', '混沌生成', and '无关概念' without clear activation boundaries, exclusions, or scoping conditions. This can cause accidental invocation in unrelated contexts and may push the agent into inappropriate 'random combination' behavior, reducing predictability and potentially bypassing safer task-specific handling.

VirusTotal

62/62 vendors flagged this skill as clean.

View on VirusTotal

Static analysis

No suspicious patterns detected.