ClawHub
Back to skill

Security audit

Env Health Check

Security checks across malware telemetry and agentic risk

Overview

This skill is a small, disclosed local health-check tool that only checks user-named environment variables and directories, then writes a local report.

Before installing or running it, pass only environment variable names and directory paths you are comfortable including in a local report, and choose an --out path that is safe to create or overwrite.

SkillSpector

By NVIDIA
Vulnerability Patterns
  • MCP Least PrivilegeUnderdeclared Capability, Wildcard Permission, Missing Permission Declaration
  • 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 (1)

Lp3

Medium
Category
MCP Least Privilege
Confidence
93% confidence
Finding
The skill explicitly instructs users to inspect environment variables, which means it relies on access to potentially sensitive process environment data, yet the skill metadata declares no permissions. This mismatch is dangerous because it hides privileged capability from policy and review systems, increasing the chance of unvetted access to secrets such as API keys, tokens, or database credentials during execution.

VirusTotal

63/63 vendors flagged this skill as clean.

View on VirusTotal

Static analysis

No suspicious patterns detected.