ClawHub
Back to skill

Security audit

容器检查入门工具

Security checks across malware telemetry and agentic risk

Overview

The skill fits container inspection, but it can expose container logs and environment variables while incorrectly promising sensitive data will not appear.

Install only if you are comfortable letting the agent inspect local containers and return logs, mounts, ports, and environment variables. Treat outputs as potentially sensitive and avoid using it on containers that store secrets in environment variables unless the agent is instructed to redact them first.

SkillSpector

Vulnerability Patterns
  • 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
  • Privilege EscalationExcessive Permissions, Sudo/Root Execution, Credential Access
  • Supply ChainUnpinned Dependencies, External Script Fetching, Obfuscated Code
Findings (1)

Intent-Code Divergence

High
Confidence
97% confidence
Finding
The skill claims that outputs do not contain sensitive data, yet it explicitly documents configuration inspection including environment variables. In container environments, environment variables frequently hold secrets such as API keys, database passwords, and tokens, so this mismatch can cause unintended secret disclosure during normal use.

VirusTotal

VirusTotal findings are pending for this skill version.

View on VirusTotal

Static analysis

No suspicious patterns detected.