This skill allows arbitrary command execution, fetches external
Claims to do
mcporter: Use `mcporter` to work with MCP servers directly.
Actually does
This skill executes the `mcporter` CLI tool to interact with MCP servers. It allows users to list available tools, call specific tools with various arguments (including JSON payloads), manage authentication (OAuth), configure `mcporter` settings (defaulting to `./config/mcporter.json`), run a daemon, and generate client-side code (CLI or TypeScript). It can also invoke `bun run` for stdio servers and contacts specified URLs for MCP server interactions.
openclaw skills install steipete/mcporterThe skill explicitly demonstrates the ability to execute arbitrary commands using `mcporter call --stdio`, allowing for direct execution of system commands or scripts with attacker-controlled input.
mcporter call --stdio "bun run ./server.ts"
The `mcporter generate-cli --command <url>` command allows fetching and processing code from an arbitrary external URL, which could be used to introduce malicious code or configurations.
mcporter generate-cli --command <url>
Commands like `mcporter auth` and `mcporter config add|import|login` can manage authentication and configuration, potentially allowing a compromised `mcporter` tool to harvest credentials or inject persistent malicious settings.
mcporter auth <server | url>, mcporter config list|get|add|remove|import|login|logout
The `mcporter daemon start` command can launch a background process, which, if the `mcporter` binary is compromised, could be used to establish persistence for malicious activities.
mcporter daemon start|status|stop|restart
The skill interacts with external URLs for fetching data or calling tools, which could potentially be abused for Server-Side Request Forgery (SSRF) if the agent is prompted to access internal or restricted resources.
mcporter call https://api.example.com/mcp.fetch url:https://example.com
[](https://mondoo.com/ai-agent-security/skills/clawhub/steipete/mcporter)<a href="https://mondoo.com/ai-agent-security/skills/clawhub/steipete/mcporter"><img src="https://mondoo.com/ai-agent-security/api/badge/clawhub/steipete/mcporter.svg" alt="Mondoo Skill Check" /></a>https://mondoo.com/ai-agent-security/api/badge/clawhub/steipete/mcporter.svgSkills can read files, run commands, and access credentials. Mondoo helps organizations manage the security risks of AI agent skills across their entire fleet.