ClawHub

Docker Helper

Security checks across malware telemetry and agentic risk

Overview

This is mostly a Docker template and command-reference skill, with one under-described local helper script that only prints status messages and writes a local history log.

Install only if you want a Docker reference and template helper. Treat generated Dockerfiles and compose files as development starting points: replace default passwords, enable service security, restrict exposed ports, and review cleanup commands before running them. Avoid passing secrets as arguments to the generic helper script because it can store them locally in command history.

SkillSpector

By NVIDIA
Vulnerability Patterns
  • MCP Least PrivilegeUnderdeclared Capability, Wildcard Permission, Missing Permission Declaration
  • 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
Findings (4)

Lp3

Medium
Category
MCP Least Privilege
Confidence
81% confidence
Finding
The skill advertises operational capabilities that imply shell and network access, but it does not declare corresponding permissions or clearly scope those actions. This creates a transparency and consent problem: users or hosting frameworks may invoke a skill with capabilities broader than expected, increasing the chance of unintended command execution or outbound access.

Tp4

High
Category
MCP Tool Poisoning
Confidence
91% confidence
Finding
There is a significant mismatch between the stated Docker-helper purpose and the broader behaviors detected, including workflow automation, build/test/deploy actions, and persistent local logging. This kind of scope expansion is dangerous because users may trust the skill for narrow advisory use while it performs broader project-affecting operations or stores usage history without clear disclosure.

Description-Behavior Mismatch

High
Confidence
93% confidence
Finding
The script materially contradicts the declared skill purpose: it presents itself as a Docker helper but implements a generic developer workflow wrapper with commands like init, check, build, test, and deploy. This mismatch is dangerous because users or higher-level agents may invoke it expecting Docker-scoped behavior, creating a trust-boundary violation that can misroute workflows, mask capabilities, and enable deceptive packaging of unrelated automation under a benign Docker-themed label.

Intent-Code Divergence

Medium
Confidence
90% confidence
Finding
The inline help and header explicitly describe a 'Developer workflow automation tool,' reinforcing that the artifact is not actually a Docker-focused helper as advertised. While not directly enabling code execution, misleading documentation increases the risk of operator or agent misuse and is a common indicator of repackaged or deceptively labeled skills.

VirusTotal

66/66 vendors flagged this skill as clean.

View on VirusTotal