ClawHub
Back to skill

Security audit

Skillhub Preference

Security checks across malware telemetry and agentic risk

Overview

This is a small instruction-only skill that openly prefers one skill registry over another and does not include hidden code or privileged behavior.

Install this only if you want your agent to try skillhub before clawhub for skill searches, installs, and updates. Review the reported source, version, publisher, and risk signals before approving any resulting 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
88% confidence
Finding
The skill description is broad enough to activate on many general requests about skills, plugins, or capability extension, which can cause this policy skill to be invoked in situations where it was not explicitly intended. That increases the chance of steering package discovery and installation behavior by default, potentially affecting supply-chain decisions or causing unnecessary tool use.

VirusTotal

66/66 vendors flagged this skill as clean.

View on VirusTotal

Static analysis

No suspicious patterns detected.