ClawHub Skill Packager

• Outcome: Pass
• Latest audit: May 29, 2026, 8:31 PM
• Version:
  1.5.2

Overview

This is a text-only skill for packaging ClawHub/OpenClaw skills, with no hidden execution, credential use, persistence, or network behavior found.

Install this for explicit ClawHub/OpenClaw skill packaging work. Because it infers missing names, metadata, and packaging details, review the generated bundle and separate review file before publishing or installing the output.

SkillSpector

By NVIDIA

Vulnerability Patterns

• Trigger Abuse: Overly Broad Trigger, Shadow Command Trigger, Keyword Baiting Trigger
• Prompt Injection: Instruction Override, Hidden Instructions, Exfiltration Commands
• Data Exfiltration: External Transmission, Env Variable Harvesting, File System Enumeration
• Privilege Escalation: Excessive Permissions, Sudo/Root Execution, Credential Access
• Supply Chain: Unpinned Dependencies, External Script Fetching, Obfuscated Code

Findings (1)

Vague Triggers

Medium

• Confidence: 93% confidence
• Finding: The activation guidance says to use the skill when the user wants to "create, repair, review, rename, repackage, or republish" a skill bundle, which is a wide set of generic intents without concrete trigger phrases, boundaries, or exclusion examples. This broad wording could cause unintended invocation for ordinary requests about reviewing or renaming files unless additional scope constraints are supplied.

VirusTotal

66/66 vendors flagged this skill as clean.