AI agents use upload_file to create or update resources in Code Box — usually the action step of a workflow, after the agent has gathered context. Every call changes real data in your Code Box environment.
Upload operations create or modify files on the server, making this a Write action. Severity is high because uploaded files could be executed by paired tools (exec_code), introduce malicious payloads, or overwrite critical artifacts in the stateful session environment.
From the tool's definition Tool name 'upload_file' with no description provided. Inferred from context: a file I/O tool on a code execution server that likely creates or modifies files. Paired with 'exec_code' and 'exec_sql' on a stateful execution platform.
Attacks that exploit this kind of access
upload_file. It is categorised as a Write tool in the Code Box MCP Server, which means it can create or modify data. Consider rate limits to prevent runaway writes.
Register the Code Box MCP server in PolicyLayer and add a rule for upload_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 Code Box. Nothing to install.
upload_file is a Write tool with medium risk. Write tools should be rate-limited to prevent accidental bulk modifications.
Yes. Add a rate_limit block to the upload_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 upload_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.
upload_file is provided by the Code Box MCP server (madhanmohanreddy2301/codeboxmcp). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.
Every MCP server has a record like this.
Type a name, get the same breakdown: verified identity, auth posture, risk grade, capabilities, recommended policy.
Teams ship this data inside their own products. See what a licence covers →