ClawHub
Back to skill

Security audit

Web Notepad Free

Security checks across malware telemetry and agentic risk

Overview

This is a plausible form-management skill, but its broad activation wording and under-emphasized irreversible delete capability need review before installation.

Review this skill before installing if the connected account contains important or sensitive form data. Use a least-privilege API key, avoid invoking it for Webhook or unrelated system-integration work, and require explicit confirmation plus export/backup before any delete operation.

SkillSpector

By NVIDIA
Vulnerability Patterns
  • Excessive AgencyUnrestricted Tool Access, Autonomous Decision Making, Scope Creep
  • Trigger AbuseOverly Broad Trigger, Shadow Command Trigger, Keyword Baiting Trigger
  • MCP Tool PoisoningHidden Instructions, Unicode Deception, Parameter Description Injection
  • Prompt InjectionInstruction Override, Hidden Instructions, Exfiltration Commands
  • Data ExfiltrationExternal Transmission, Env Variable Harvesting, File System Enumeration
Findings (3)

Intent-Code Divergence

Medium
Confidence
97% confidence
Finding
The skill states in multiple places that the free edition does not support Webhook subscriptions, yet the trigger conditions say it should be used for Webhook configuration. This contradiction can cause an agent or user to invoke the skill for unsupported integration work, leading to mis-execution, confusion, and potentially unsafe fallback behavior if the agent improvises commands outside the documented safe scope.

Vague Triggers

Medium
Confidence
89% confidence
Finding
The trigger condition '需要API集成、接口对接、Webhook配置、系统连接时使用' is overly broad and can cause the agent to select this skill for many unrelated integration tasks. Overbroad activation increases the chance of unintended external API calls, misuse of credentials, and execution of destructive operations in contexts the skill was not designed for.

Missing User Warnings

Medium
Confidence
86% confidence
Finding
The skill advertises full lifecycle management including delete operations near the top-level capability summary, but the irreversible cascading deletion risk is only disclosed later in the FAQ. This makes it easier for an agent or user to invoke destructive actions without seeing a prominent warning first, increasing the chance of accidental data loss.

VirusTotal

VirusTotal findings are pending for this skill version.

View on VirusTotal

Static analysis

No suspicious patterns detected.