ClawHub
Back to skill

Security audit

Automated Content Machine

Security checks across malware telemetry and agentic risk

Overview

This skill is openly for automatic public content publishing, but it lacks clear approval and account-scope safeguards, so it should be reviewed before use.

Install only if you intend to let an agent prepare content for connected publishing accounts. Use draft-only or test accounts first, grant the narrowest possible service permissions, require explicit approval before any post, newsletter, blog entry, or product promotion goes live, and keep a clear rollback process for published content.

SkillSpector

By NVIDIA
Vulnerability Patterns
  • Data ExfiltrationExternal Transmission, Env Variable Harvesting, File System Enumeration
  • Prompt InjectionInstruction Override, Hidden Instructions, Exfiltration Commands
  • 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
Findings (2)

Missing User Warnings

Medium
Confidence
88% confidence
Finding
The skill explicitly markets '自動發布到多平台' in its top-level description but provides no warning that it may post content to connected third-party accounts and sites. This can lead users to authorize actions that publish unintended, low-quality, or policy-violating content across their channels, creating reputational and account-level risk.

Missing User Warnings

Medium
Confidence
90% confidence
Finding
Describing automatic publishing to WordPress/Ghost without any caution obscures that the skill can change external websites, potentially creating or updating public posts. In a content automation context, this increases the chance of accidental publication, spam, SEO damage, or misuse of connected CMS credentials.

VirusTotal

64/64 vendors flagged this skill as clean.

View on VirusTotal

Static analysis

No suspicious patterns detected.