ClawHub
Back to skill

Security audit

CrazeeOpenclawSkill

Security checks for vulnerabilities and agentic risk

Overview

This skill is a simple coordination guide for routing OpenClaw work among agents, with no bundled code, persistence, credential handling, or hidden behavior found.

Install this only if you want OpenClaw tasks routed through the described Claude, Gemini CLI, and Codex CLI workflow. Review the hard-coded role mapping first, especially in environments where agent selection should be user-controlled or policy-driven.

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 (2)

Vague Triggers

Medium
Confidence
93% confidence
Finding
The skill’s activation criteria are very broad: it applies whenever tasks involve coordination, assignment, subtasks, collaboration, or frontend/backend division. In an agentic system, vague triggers can cause the skill to activate in unintended contexts and impose routing/coordination behavior that overrides more appropriate user-directed or task-specific handling.

Natural-Language Policy Violations

Low
Confidence
82% confidence
Finding
The skill hard-codes role assignments to specific CLIs and workflows without user choice or policy-based selection. This can reduce operator control and may route work to tools that are unnecessary, unavailable, or less appropriate, increasing the chance of mis-execution or policy drift in multi-agent environments.

Static analysis

No suspicious patterns detected.