This record as markdown: /tools/cowork-os/cloud-sandbox-read-file.md
What cloud_sandbox_read_file does on CoWork OS
AI agents call cloud_sandbox_read_file to retrieve information from CoWork OS without modifying anything. It is typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
Why cloud_sandbox_read_file is rated Low
This tool retrieves file contents from a cloud sandbox environment. It performs a read-only operation with no side effects, no data modification, and no execution of code. The blast radius is minimal: worst case, an AI agent reads unintended file contents, but cannot alter, delete, or execute anything. Classified as Read with low severity.
From the tool's definition Tool name contains 'read_file' and description states 'Read a file from a cloud sandbox' — indicates data retrieval without modification.
Attacks that exploit this kind of access
The rule that runs cloud_sandbox_read_file 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_read_file, this is the rule to start with:
cloud_sandbox_read_file is read-only, so it stays allowed. 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_read_file call is checked against it from then on.
Questions about cloud_sandbox_read_file
Read a file from a cloud sandbox. It is categorised as a Read tool in the CoWork OS MCP Server, which means it retrieves data without modifying state.
Register the CoWork OS MCP server in PolicyLayer and add a rule for cloud_sandbox_read_file: 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_read_file is a Read tool with low risk. Read-only tools are generally safe to allow by default.
Yes. Add a rate_limit block to the cloud_sandbox_read_file 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_read_file. 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_read_file 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.
This server
Across the catalogue