ClawHub

Skill Search & Create

Security checks across malware telemetry and agentic risk

Overview

This skill is a straightforward ClawHub helper for searching, creating, and optionally publishing skills, with account-affecting actions disclosed and mostly user-directed.

Install this only if you want an agent to help manage OpenClaw skills through the ClawHub CLI. Confirm before any create or publish action, review generated skill contents and metadata before publishing, and make sure the CLI is logged into the intended ClawHub account.

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
85% confidence
Finding
The skill description says it will search for existing skills and automatically create a new one when no match is found, but the workflow later says creation should happen only after asking for confirmation. This ambiguity can cause an agent to perform state-changing actions unexpectedly, such as scaffolding or preparing a new skill without clear user consent, which is risky in an agentic environment.

VirusTotal

66/66 vendors flagged this skill as clean.

View on VirusTotal