run_shell · Hermes Computer Use MCP: Risk & Policy

WHAT IT DOES

What run_shell does on Hermes Computer Use

AI agents invoke run_shell to trigger actions in Hermes Computer Use. 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.

WHY IT NEEDS A POLICY

Why run_shell needs a policy

Shell command execution is a classic Execute-category capability with critical severity due to unrestricted blast radius. An AI agent with access to this tool can invoke virtually any operation: data exfiltration, lateral movement, process manipulation, network access, or system modification.

From the tool's definition Tool description explicitly states "Run a shell command" with examples like `ls`, `curl`, and "file ops". This directly executes arbitrary shell commands in WSL, which can perform any operation the WSL user can perform.

Attacks that exploit this kind of access

Recommended rule Ready

Verdict

run_shell Rate-limited

run_shell 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.

View as policy code

policy.json

{
  "version": "1",
  "default": "deny",
  "tools": {
    "run_shell": {
      "limits": [
        {
          "counter": "run_shell_rate",
          "window": "minute",
          "max": 10,
          "scope": "grant"
        }
      ]
    }
  }
}

RATE-LIMIT THIS TOOL →

Instant setup, no code required.

PolicyLayer is an MCP gateway: every tool call is checked against your rule before it reaches Hermes Computer Use, so you can run agents against it safely.

FAQ

Questions about run_shell

What does the run_shell tool do? +

Run a shell command inside WSL (for ops like ls, curl, file ops). It is categorised as a Execute tool in the Hermes Computer Use MCP Server, which means it can trigger actions or run processes. Use rate limits and argument validation.

How do I enforce a policy on run_shell? +

Register the Hermes Computer Use MCP server in PolicyLayer and add a rule for run_shell: 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 Hermes Computer Use. Nothing to install.

What risk level is run_shell? +

run_shell is a Execute tool with high risk. Execute tools should be rate-limited and have argument validation enabled.

Can I rate-limit run_shell? +

Yes. Add a rate_limit block to the run_shell 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.

How do I block run_shell completely? +

Set action: deny in the PolicyLayer policy for run_shell. 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.

What MCP server provides run_shell? +

run_shell is provided by the Hermes Computer Use MCP server (noah3521/hermes-computer-use). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.