ClawHub

CrazeeOpenclawSkill

Security checks across malware telemetry and agentic risk

Overview

This is a visible, instruction-only coordination skill for routing OpenClaw work between agents, with no code, persistence, credential access, or hidden behavior.

Install this only if you want OpenClaw-style delegation among Claude, Gemini CLI, and Codex CLI. For sensitive projects, confirm what those delegated CLI agents can access before routing private task details through this workflow.

SkillSpector

By NVIDIA
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
89% confidence
Finding
The skill description is broadly scoped to routine coordination activities such as task assignment, subtask creation, multi-agent collaboration, and QA flow, which can cause it to activate for many ordinary requests. Over-broad activation increases the chance that this skill intercepts prompts unnecessarily, influencing workflow routing and agent behavior in ways the user did not explicitly request.

Natural-Language Policy Violations

Medium
Confidence
80% confidence
Finding
The skill metadata and content are written to enforce Chinese-language behavior without presenting language choice or a justified restriction. This can cause unexpected behavior, reduced usability, or miscoordination when users or collaborating agents operate in other languages, especially in mixed-language environments.

VirusTotal

59/59 vendors flagged this skill as clean.

View on VirusTotal