ClawHub
Back to skill

Security audit

agent-ready

Security checks across malware telemetry and agentic risk

Overview

This skill asks an agent to audit and improve a Ghost site for AI discoverability, and its higher-impact CMS actions are disclosed and gated by owner approval and verification.

Install only if you are comfortable giving the agent scoped Ghost access to publish pages and append site header metadata. Use a dedicated staff account, review all public copy before approval, and keep API keys out of repositories as the skill instructs.

SkillSpector

By NVIDIA
Vulnerability Patterns
  • Supply ChainUnpinned Dependencies, External Script Fetching, Obfuscated Code
  • Prompt InjectionInstruction Override, Hidden Instructions, Exfiltration Commands
  • Data ExfiltrationExternal Transmission, Env Variable Harvesting, File System Enumeration
  • Privilege EscalationExcessive Permissions, Sudo/Root Execution, Credential Access
  • Excessive AgencyUnrestricted Tool Access, Autonomous Decision Making, Scope Creep
Findings (1)

External Script Fetching

High
Category
Supply Chain
Content
# Verification Commands

All curl and shell commands used across the 9-item checklist, collected in one place
for quick reference. Run these as part of Gate 4 after each step — do not rely on API
success responses alone.
Confidence
27% confidence
Finding
Remote code is downloaded and executed. This bypasses code review and could introduce malicious code.

VirusTotal

62/62 vendors flagged this skill as clean.

View on VirusTotal

Static analysis

No suspicious patterns detected.