ClawHub
Back to skill

Security audit

Uncle Matt's Caveman Curse

Security checks across malware telemetry and agentic risk

Overview

The skill appears to be a disclosed response-style mode with profanity persistence, which is a usability and professionalism risk but not evidence of malware or hidden system access.

Install only if you intentionally want this response style. Use the reset phrases before professional, educational, compliance, or sensitive conversations, and avoid enabling it in shared or age-unknown settings.

SkillSpector

By NVIDIA
Vulnerability Patterns
  • Data ExfiltrationExternal Transmission, Env Variable Harvesting, File System Enumeration
  • Prompt InjectionInstruction Override, Hidden Instructions, Exfiltration Commands
  • 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
95% confidence
Finding
The skill explicitly makes a profane, persistent response mode active across future turns once triggered, with reversion only through specific user phrases. That creates a behavioral hijack risk: it can override expected assistant tone and safety-sensitive communication style, increasing the chance of inappropriate outputs in professional, educational, or sensitive contexts.

VirusTotal

63/63 vendors flagged this skill as clean.

View on VirusTotal

Static analysis

No suspicious patterns detected.