ClawHub
Back to skill

Security audit

hekouwang-env-doctor-skill

Security checks across malware telemetry and agentic risk

Overview

This skill is a disclosed development-environment disk scanner and interactive cleaner with user confirmation controls, not hidden or automatic cleanup behavior.

Install only if you want an agent to inspect developer-tool storage under your home directory. Use the scan first, prefer clean.sh --dry-run before real cleanup, and review every selected item because the cleaner can remove whitelisted cache or old tool directories after confirmation.

SkillSpector

By NVIDIA
Vulnerability Patterns
  • 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
  • Supply ChainUnpinned Dependencies, External Script Fetching, Obfuscated Code
Findings (2)

Vague Triggers

Medium
Confidence
88% confidence
Finding
The README includes a very broad natural-language trigger example ('磁盘满了，帮我看看什么占了空间') and the metadata also lists many everyday phrases that could match ordinary conversation. In a skill that can lead to filesystem cleanup actions, overly broad invocation increases the chance of accidental activation, which can steer a session toward scanning local disk usage and presenting deletion workflows the user did not explicitly intend to start.

Vague Triggers

Medium
Confidence
84% confidence
Finding
The trigger conditions are very broad, including many generic phrases about disk space or cleanup, which can cause the skill to activate in contexts where the user did not intend a development-environment scan. In an agent setting, unintended invocation increases the chance of unnecessary filesystem enumeration and presenting cleanup actions for the wrong task context, which is risky even if the skill claims confirmation before deletion.

VirusTotal

63/63 vendors flagged this skill as clean.

View on VirusTotal

Static analysis

No suspicious patterns detected.