cloud_sandbox_exec
Execute a shell command in a cloud sandbox. Returns stdout, stderr, and exit code.
This record as markdown: /tools/cowork-os/cloud-sandbox-exec.md
What cloud_sandbox_exec does on CoWork OS
AI agents invoke cloud_sandbox_exec to trigger actions in CoWork OS. 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 cloud_sandbox_exec is rated High
This tool runs arbitrary shell commands in a cloud environment, which can perform any operation depending on what command is passed. The effects are determined by the arguments and are not reversible in many cases (though deletion is not the primary purpose). The blast radius is high because an AI agent could execute commands that modify files, exfiltrate data, install software, or pivot to other systems.
From the tool's definition Tool explicitly states 'Execute a shell command in a cloud sandbox.' Shell command execution is the canonical Execute operation.
Attacks that exploit this kind of access
The rule that runs cloud_sandbox_exec safely
PolicyLayer is an MCP gateway: it sits between your AI agents and CoWork OS, and checks every tool call against a rule you set before the call runs. Nothing changes on the server itself. For cloud_sandbox_exec, this is the rule to start with:
cloud_sandbox_exec 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 CoWork OS, apply this rule, and every cloud_sandbox_exec call is checked against it from then on.
Questions about cloud_sandbox_exec
Execute a shell command in a cloud sandbox. Returns stdout, stderr, and exit code. It is categorised as a Execute tool in the CoWork OS MCP Server, which means it can trigger actions or run processes. Use rate limits and argument validation.
Register the CoWork OS MCP server in PolicyLayer and add a rule for cloud_sandbox_exec: 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 CoWork OS. Nothing to install.
cloud_sandbox_exec 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 cloud_sandbox_exec 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 cloud_sandbox_exec. 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.
cloud_sandbox_exec is provided by the CoWork OS MCP server (CoWork-OS/CoWork-OS). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.
More on CoWork OS, and thousands of servers like it.
Across the catalogue