AI agents invoke confirm_command to trigger actions in Mcp Wsl Exec. What it does depends on the arguments the agent supplies, and its effects often reach beyond the immediate call — builds kicked off, notifications sent, workflows started.
This tool explicitly confirms execution of commands already flagged as 'dangerous'. Despite the server's claim of safety validation, this tool is the gate that allows dangerous commands to proceed. Misuse by an AI agent could result in arbitrary dangerous command execution in a WSL/Linux environment, giving it critical severity.
From the tool's definition 'confirm_command' - 'Confirm dangerous command execution'
Documented attack patterns abuse exactly the kind of access confirm_command gives an agent:
PolicyLayer is an MCP gateway — it sits between your AI agents and Mcp Wsl Exec, and nothing reaches the server without passing your rules. This is the rule we recommend for confirm_command:
{
"version": "1",
"default": "deny",
"tools": {
"confirm_command": {
"limits": [
{
"counter": "confirm_command_rate",
"window": "minute",
"max": 10,
"scope": "grant"
}
]
}
}
}confirm_command stays usable, but rate-capped — a runaway agent can't fire it dozens of times a minute. Everything else on the server is denied unless you say otherwise.
Free to start. No card required.
Confirm dangerous command execution. It is categorised as a Execute tool in the Mcp Wsl Exec MCP Server, which means it can trigger actions or run processes. Use rate limits and argument validation.
Register the Mcp Wsl Exec MCP server in PolicyLayer and add a rule for confirm_command: allow, deny, rate-limit, or require approval. Point your MCP client at the PolicyLayer proxy URL and the rule is enforced on every call, before it reaches Mcp Wsl Exec. Nothing to install.
confirm_command is a Execute tool with high risk. Execute tools should be rate-limited and have argument validation enabled.
Yes. Add a rate_limit block to the confirm_command rule in your PolicyLayer policy. For example, setting max: 10 and window: 60 limits the tool to 10 calls per minute. Rate limits are tracked per agent session and reset automatically.
Set action: deny in the PolicyLayer policy for confirm_command. The AI agent will receive a policy violation error and cannot call the tool. You can also include a reason field to explain why the tool is blocked.
confirm_command is provided by the Mcp Wsl Exec MCP server (spences10/mcp-wsl-exec). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.
Start from Mcp Wsl Exec, add the rest of your stack, and see everything your agents can call. Then put policy on all of it.
Free to start. No card required.
7 Mcp Wsl Exec tools catalogued and risk-classified — across an index of 43,000+ MCP servers.