ClawHub
Back to skill

Security audit

Ai Productivity Audit

Security checks across malware telemetry and agentic risk

Overview

This skill is a disclosed freemium AI-tool audit that asks for proportionate subscription details and only offers optional local report saving.

Install if you are comfortable with a freemium audit that includes a paid upsell and with sharing your AI-tool subscription names, approximate costs, and usage habits. If you export the report, confirm the exact filename and location first.

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
Findings (1)

Missing User Warnings

Medium
Confidence
95% confidence
Finding
The skill explicitly offers to write output to a filesystem path under the user's home directory without any safety notice, consent flow, or guidance to confirm the exact destination. In an agent setting, even a seemingly harmless export action can cause unintended local file modification, overwrite existing files, or normalize unsafe behavior where the agent performs side effects without clear user acknowledgement.

VirusTotal

64/64 vendors flagged this skill as clean.

View on VirusTotal

Static analysis

No suspicious patterns detected.