ClawHub
Back to skill

Security audit

密码生成器Pro免费版

Security checks across malware telemetry and agentic risk

Overview

This skill is a local password generator and checker with disclosed command/file access, and I found no hidden exfiltration, persistence, or destructive behavior.

Install only if you are comfortable granting the skill local command execution and file-read capability. Use it for local password generation/checking, avoid callback-style workflows for real passwords, and do not point it at password files unless you intend that audit.

SkillSpector

By NVIDIA
Vulnerability Patterns
  • Excessive AgencyUnrestricted Tool Access, Autonomous Decision Making, Scope Creep
  • Trigger AbuseOverly Broad Trigger, Shadow Command Trigger, Keyword Baiting Trigger
  • Prompt InjectionInstruction Override, Hidden Instructions, Exfiltration Commands
  • Data ExfiltrationExternal Transmission, Env Variable Harvesting, File System Enumeration
  • Privilege EscalationExcessive Permissions, Sudo/Root Execution, Credential Access
Findings (3)

Context-Inappropriate Capability

Medium
Confidence
90% confidence
Finding
The skill requests generic exec access even though its core functions are simple local password generation and strength evaluation that could be implemented without shell execution. Broad execution capability expands the attack surface: if an agent invokes this skill or follows future prompt paths through exec, it could run unintended local commands or process sensitive local data beyond the stated scope.

Vague Triggers

Medium
Confidence
86% confidence
Finding
Overly broad invocation language can cause accidental triggering for generic user requests, increasing the chance that an agent routes unrelated prompts into this skill. In a skill with exec capability, misrouting becomes more dangerous because normal conversation could unexpectedly activate code paths or command execution behaviors.

Vague Triggers

Medium
Confidence
88% confidence
Finding
The sample trigger phrase '执行核心功能' is so generic that it overlaps with ordinary user language and could spuriously activate the skill. Because the skill advertises exec support, accidental invocation may lead to unnecessary local execution or processing outside the user's intended task.

VirusTotal

65/65 vendors flagged this skill as clean.

View on VirusTotal

Static analysis

No suspicious patterns detected.