Skill Release Pipeline

• Outcome: Pass
• Latest audit: May 29, 2026 at 8:27 PM UTC
• Version:
  1.0.0

Overview

This skill does what it says: it helps publish OpenClaw skills to GitHub and ClawHub, but users should review files before running the push/publish scripts.

Before running the GitHub or full publish scripts, inspect the target skill folder, run git status, confirm the remote repository and ClawHub slug, and make sure no private files or secrets will be included by git add -A.

SkillSpector

By NVIDIA

Vulnerability Patterns

• Data Exfiltration: External Transmission, Env Variable Harvesting, File System Enumeration
• Prompt Injection: Instruction Override, Hidden Instructions, Exfiltration Commands
• Privilege Escalation: Excessive Permissions, Sudo/Root Execution, Credential Access
• Supply Chain: Unpinned Dependencies, External Script Fetching, Obfuscated Code
• Excessive Agency: Unrestricted Tool Access, Autonomous Decision Making, Scope Creep

Findings (1)

Missing User Warnings

Medium

• Confidence: 91% confidence
• Finding: The script stages all files, commits them, and pushes to a user-specified GitHub repository without any confirmation prompt, dry-run, filtering, or warning that repository contents will be transmitted off-host. In an agent or automation context, this creates a real risk of unintentionally exfiltrating secrets, local credentials, build artifacts, or other sensitive files that happen to be present in the folder.

VirusTotal

60/60 vendors flagged this skill as clean.