ClawHub
Back to skill

Security audit

Qa Skill

Security checks across malware telemetry and agentic risk

Overview

The skill appears purpose-aligned, with the main caution that it may create test files in the workspace.

Before installing, understand that the skill may write test files into your workspace. Use it in a repository where you can review diffs, and avoid running it on sensitive or uncommitted work unless you are comfortable with development-file changes.

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
92% confidence
Finding
The skill explicitly states it will automatically create test files in the workspace, but it does not clearly warn the user or require confirmation before modifying files. In an agentic pipeline, silent writes can surprise users, overwrite existing artifacts, or be chained with other skills to produce unintended repository changes.

VirusTotal

66/66 vendors flagged this skill as clean.

View on VirusTotal

Static analysis

No suspicious patterns detected.