ClawHub
Back to skill

Security audit

Crayfish Uncle

Security checks for vulnerabilities and agentic risk

Overview

This is a disclosed persona/dialect skill with no executable code or hidden high-impact behavior found.

Install this only if you want OpenClaw to respond in the described Henan-dialect uncle persona by default. Review the available configuration options if you need lower dialect intensity or less humor.

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
  • 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)

Natural-Language Policy Violations

Medium
Confidence
95% confidence
Finding
The skill explicitly states that, once installed, the assistant will speak in a specific Henan dialect/persona, and the examples reinforce that behavior as a default rather than a user-selectable mode. This can override user expectations, reduce clarity or accessibility for users who do not understand the dialect, and create an unwanted persistent persona without clear opt-in.

Static analysis

No suspicious patterns detected.