This record as markdown: /tools/openclaw/bash.md
What bash does on OpenClaw
AI agents invoke bash to trigger actions in OpenClaw. 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 bash is rated High
Running host commands is a quintessential Execute operation with maximal blast radius. An AI agent with access to bash can read files, modify system state, install malware, exfiltrate data, pivot to other systems, or destroy infrastructure—all depending on the arguments provided and the privilege level of the process. This warrants critical severity regardless of conditional language ('if enabled').
From the tool's definition Tool description states 'Run a host command (if enabled)'. This directly invokes arbitrary shell commands on the host system.
Attacks that exploit this kind of access
The rule that runs bash safely
PolicyLayer is an MCP gateway: it sits between your AI agents and OpenClaw, and checks every tool call against a rule you set before the call runs. Nothing changes on the server itself. For bash, this is the rule to start with:
bash 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.
The button opens the PolicyLayer dashboard: create your workspace, connect OpenClaw, apply this rule, and every bash call is checked against it from then on.
Questions about bash
Run a host command (if enabled). It is categorised as a Execute tool in the OpenClaw MCP Server, which means it can trigger actions or run processes. Use rate limits and argument validation.
Register the OpenClaw MCP server in PolicyLayer and add a rule for bash: 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 OpenClaw. Nothing to install.
bash 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 bash 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 bash. 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.
bash is provided by the OpenClaw MCP server (openclaw). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.
More on OpenClaw, and thousands of servers like it.
Across the catalogue