ClawHub
Back to skill

Security audit

Mcporter

Security checks across malware telemetry and agentic risk

Overview

This skill is a transparent guide for using the mcporter CLI, with broad but disclosed MCP, network, auth, config, daemon, and stdio capabilities.

Install this only if you want an agent to operate mcporter directly. Treat `mcporter call`, `--stdio`, OAuth, config edits, and daemon commands as sensitive: use trusted servers and commands, review local scripts before stdio execution, and avoid production credentials unless the action is intentional.

SkillSpector

By NVIDIA
Vulnerability Patterns
  • Data ExfiltrationExternal Transmission, Env Variable Harvesting, File System Enumeration
  • Prompt InjectionInstruction Override, Hidden Instructions, Exfiltration Commands
  • Privilege EscalationExcessive Permissions, Sudo/Root Execution, Credential Access
  • Supply ChainUnpinned Dependencies, External Script Fetching, Obfuscated Code
  • Excessive AgencyUnrestricted Tool Access, Autonomous Decision Making, Scope Creep
Findings (3)

Missing User Warnings

Medium
Confidence
89% confidence
Finding
The skill advertises capabilities to edit configuration, authenticate to servers, and invoke MCP servers over HTTP or stdio, but it does not warn that some commands can change local state or spawn local processes. In an agent-skill context, omission of these safety boundaries can lead to unintended execution or persistent config changes when the user expects read-only inspection.

Missing User Warnings

Medium
Confidence
96% confidence
Finding
The `--stdio` example demonstrates executing a local command (`bun run ./server.ts`) without any warning that this launches an arbitrary local process. In a skill consumed by an automated agent, such an example can normalize or encourage unsafe local code execution, which may run untrusted scripts with the user's privileges.

Missing User Warnings

Low
Confidence
91% confidence
Finding
The configuration and auth commands are documented as routine operations but may alter local configuration state, credentials, or session state. Without warning, a user or agent may invoke them assuming they are informational, causing unintended persistence or account/session changes.

VirusTotal

63/63 vendors flagged this skill as clean.

View on VirusTotal

Static analysis

No suspicious patterns detected.