AI agents use upload_from_url to create or update resources in Yadisk — usually the action step of a workflow, after the agent has gathered context. Every call changes real data in your Yadisk environment.
This tool creates or modifies data reversibly by uploading a file to cloud storage. While it involves fetching from an external URL, the primary effect is writing data to Yandex Disk. It is not Destructive (data is not deleted), not Execute (no arbitrary code execution), and not Financial.
From the tool's definition Tool description states 'Upload a file to Yandex Disk' which creates new data on the storage service. The tool downloads from a remote URL and stores the result, making it a write operation that modifies the user's disk state.
Attacks that exploit this kind of access
Upload a file to Yandex Disk by downloading it from a remote URL. It is categorised as a Write tool in the Yadisk MCP Server, which means it can create or modify data. Consider rate limits to prevent runaway writes.
Register the Yadisk MCP server in PolicyLayer and add a rule for upload_from_url: 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 Yadisk. Nothing to install.
upload_from_url 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_from_url 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_from_url. 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_from_url is provided by the Yadisk MCP server (patr56/yadisk-mcp). 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 →