AI agents use files_shared_public_url 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.
This tool modifies the sharing state of a file by enabling public/external access. While technically reversible (sharing can be disabled), it represents a significant Write action that exposes files to external parties. It is not Destructive because the file itself is not deleted or overwritten, and not Execute because no arbitrary code/commands are run.
From the tool's definition Tool name 'files_shared_public_url' and description 'Enable a file for public/external sharing' indicate modification of file sharing settings, which changes data access permissions irreversibly until reversed.
Attacks that exploit this kind of access
Enable a file for public/external sharing. 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_shared_public_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 Slack. Nothing to install.
files_shared_public_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 files_shared_public_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 files_shared_public_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.
files_shared_public_url 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 →