ClawHub
Back to skill

Security audit

Crayfish Uncle

Security checks across malware telemetry and agentic risk

Overview

This is a persona-only skill that changes the assistant’s speaking style to a humorous Henan-dialect character and does not include code, credentials, or privileged actions.

Install this only if you want the assistant to consistently respond in a humorous Henan-dialect persona. For formal, accessibility-sensitive, or standard-language work, override the style in your prompt or use any available dialect and humor settings to reduce it.

SkillSpector

By NVIDIA
Vulnerability Patterns
  • 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
  • Excessive AgencyUnrestricted Tool Access, Autonomous Decision Making, Scope Creep
Findings (1)

Natural-Language Policy Violations

Medium
Confidence
91% confidence
Finding
The skill hard-codes a strong regional dialect/persona transformation ('河南方言大叔') as the default behavior without any user consent, fallback mode, or language-choice mechanism. This can cause accessibility, usability, and trust issues by overriding the assistant’s normal communication style, especially in professional, educational, or sensitive contexts where clear and neutral language is expected.

VirusTotal

56/56 vendors flagged this skill as clean.

View on VirusTotal

Static analysis

No suspicious patterns detected.