AI agents use send_file_to_chat to create or update resources in Teams — usually the action step of a workflow, after the agent has gathered context. Every call changes real data in your Teams environment.
This tool creates new message data in Teams chats by uploading files and attaching them. This is a reversible write operation—messages can be deleted and files removed. It does not execute code, delete data irreversibly, or move money. The severity is medium because misuse could flood chats with unwanted files, but the action is not irreversible and the blast radius is limited to a single chat or set of chats.
From the tool's definition The tool performs 'Upload a local file and send it as a message to a Teams chat.' This creates and modifies chat data by adding new file attachments to a conversation.
Attacks that exploit this kind of access
Upload a local file and send it as a message to a Teams chat. Supports any file type (PDF, DOCX, ZIP, images, etc.). The file is uploaded to OneDrive and sent as a reference attachment. It is categorised as a Write tool in the Teams MCP Server, which means it can create or modify data. Consider rate limits to prevent runaway writes.
Register the Teams MCP server in PolicyLayer and add a rule for send_file_to_chat: 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 Teams. Nothing to install.
send_file_to_chat 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 send_file_to_chat 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 send_file_to_chat. 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.
send_file_to_chat is provided by the Teams MCP server (@floriscornel/teams-mcp). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.