AI agents use files_remote_add 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 'add' action typically creates or modifies data reversibly. The empty description reduces confidence, but the name strongly implies adding remote file references to Slack—a Write operation. In a Slack context with broad file access, this could modify workspace state and potentially affect collaboration, justifying high severity. Without more detail, confidence is moderate-to-high at 0.72.
From the tool's definition Tool name 'files_remote_add' with 'add' verb indicates creation/modification of remote file references. Description is empty, limiting direct confirmation.
Attacks that exploit this kind of access
files_remote_add. 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_remote_add: 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_remote_add 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_remote_add 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_remote_add. 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_remote_add 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 →