ClawHub
Back to skill

Security audit

Web漏洞评估(免费版)

Security checks across malware telemetry and agentic risk

Overview

This is a disclosed web security checklist skill, with no artifact evidence of hidden execution, persistence, credential theft, or destructive behavior.

Install only for assessing applications you own or are authorized to test. Review any generated commands before running them, and avoid using callback URLs unless you trust the endpoint and understand what report data may be sent.

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 (1)

Missing User Warnings

Medium
Confidence
91% confidence
Finding
The skill advertises access to exec, write, and callback_url-driven behavior without clearly warning users that it may execute shell commands, write files, or transmit data over the network. In an agent setting, this increases the risk of unintended command execution, unsafe file export, or exfiltration to attacker-controlled URLs if later prompts or workflows use these capabilities implicitly.

VirusTotal

64/64 vendors flagged this skill as clean.

View on VirusTotal

Static analysis

No suspicious patterns detected.