ClawHub
Back to skill

Security audit

ranbing

Security checks across malware telemetry and agentic risk

Overview

This is a prompt-only Chinese clarification and rewriting helper; its broad activation may be noisy, but it does not install code, access credentials, or run tools.

Install this if you want a Chinese-language helper for clarifying vague requests, rewriting text in a casual style, and preparing agent handoff templates. Be aware it may activate on broad or ambiguous phrasing and may steer outputs into its Chinese, playful style, so review formal or multi-agent outputs before relying on them.

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
76% confidence
Finding
The skill states it will auto-activate for any vague or incomplete instruction, which creates ambiguous routing boundaries and can cause the agent to intercept many unrelated requests. In multi-skill environments, this can override user intent, leak context into unnecessary clarification flows, or trigger delegation behavior when the user did not explicitly request it.

VirusTotal

66/66 vendors flagged this skill as clean.

View on VirusTotal