AI agents use files_upload_v2 to create or update resources in Slack — usually the action step of a workflow, after the agent has gathered context. Every call changes real data in your Slack environment.
The tool name 'files_upload_v2' clearly indicates it uploads files to Slack, which is a write operation that creates or modifies data. This is reversible (files can be deleted), so it does not qualify as Destructive. The severity is high because uploading files to Slack channels could distribute malicious content, overwrite important information, or compromise workspace integrity if an AI agent is compromised.
From the tool's definition Tool name 'files_upload_v2' indicates file upload functionality. The server description states it 'Provides LLMs full access to Slack: messages, channels, files, canvases, lists' and mentions 220 tools for comprehensive Slack access.
Attacks that exploit this kind of access
files_upload_v2. It is categorised as a Write tool in the Slack MCP Server, which means it can create or modify data. Consider rate limits to prevent runaway writes.
Register the Slack MCP server in PolicyLayer and add a rule for files_upload_v2: 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 Slack. Nothing to install.
files_upload_v2 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 files_upload_v2 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 files_upload_v2. 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.
files_upload_v2 is provided by the Slack MCP server (karbassi/slack-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 →