ClawHub
Back to skill

Security audit

Uncle Matt's Caveman Curse

Security checks for vulnerabilities and agentic risk

Overview

This is a disclosed text-style skill that makes responses terse and profane, with no file, network, credential, execution, or system-persistence behavior.

Install only if you intentionally want an opt-in terse, profane response style. Avoid using it in workplace, client-facing, educational, or sensitive conversations where profanity would be inappropriate, and use the documented stop phrases to return to normal mode.

A.I.G

Vulnerability Patterns
  • Skill Instruction HijackingAlters the agent's session goals or safety constraints when the skill loads
  • Agent Memory PoisoningWrites attacker-controlled rules into memory that affect later sessions
  • Remote Payload Retrieval and ExecutionFetches external code whose behavior can change after review
  • Embedded Malicious CodeShips malicious scripts inside the skill and executes them locally
  • Unauthorized Access and Privilege EscalationObtains permissions beyond the task's legitimate needs

SkillSpector

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
Category
Not specified by scanner
Confidence
95% confidence
Finding

The skill explicitly sets a profane default tone and requires profanity in non-trivial responses once triggered, which can cause the agent to generate inappropriate or policy-violating output without task-specific user consent. This is more dangerous because the behavior is persistent across turns, making accidental activation or continued misuse more likely in otherwise normal or professional contexts.

Content

No source excerpt is available for this finding.

Static analysis

No suspicious patterns detected.