ClawHub
Back to skill

Security audit

99999

Security checks across malware telemetry and agentic risk

Overview

This is a straightforward guide for creating Claude Code/OpenClaw skills, with no hidden executable behavior found.

Reasonable to install if you want help authoring skills. Review any generated personal or project skills before keeping or sharing them, because they can persist and affect future agent behavior.

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 frontmatter description is overly broad and includes generic terms like creating, writing, authoring, or designing a new Skill. In an agentic routing system, this can cause the skill to activate for loosely related requests and unintentionally steer the model into a broader set of behaviors than intended.

VirusTotal

63/63 vendors flagged this skill as clean.

View on VirusTotal

Static analysis

No suspicious patterns detected.