ClawHub

Claude Skill

Security checks across malware telemetry and agentic risk

Overview

This is a large OpenClaw skill directory that does not run code itself, but users should review any third-party skill before installing it.

Use this as a catalog, not as proof that listed skills are safe. Before installing a recommended skill, check its source, publisher, permissions, and ClawHub/security scan results, especially for skills involving credentials, wallets, posting, automation, or global installation.

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 (1)

Vague Triggers

Medium
Confidence
91% confidence
Finding
The skill is designed to activate on very generic requests about finding, installing, or choosing skills, which can cause it to trigger in many ordinary conversations. In a directory skill that can recommend and facilitate installation of third-party community skills, over-triggering increases the chance of unsolicited recommendations and accidental exposure to risky supply-chain suggestions, even though the file itself includes some security warnings.

VirusTotal

64/64 vendors flagged this skill as clean.

View on VirusTotal