ClawHub
Back to skill

Security audit

Multi-Channel Skill Publisher

Security checks across malware telemetry and agentic risk

Overview

This skill is a publishing checklist for releasing one skill across ClawHub and Claude Code channels, with no hidden code or automatic behavior found.

Install this only if you want an agent to help publish skills/plugins across registries. Before following its release commands, review git status/diffs, confirm versions and slugs, and ensure no private files or secrets would be pushed to a public repository or published package.

SkillSpector

By NVIDIA
Vulnerability Patterns
  • 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
  • Excessive AgencyUnrestricted Tool Access, Autonomous Decision Making, Scope Creep

VirusTotal

36/36 vendors flagged this skill as clean.

View on VirusTotal

Static analysis

No suspicious patterns detected.