AI agents use bookmarks_edit 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 'edit' verb indicates reversible modification of bookmarks within Slack. Without a detailed description, confidence is moderate. Severity is medium because bookmark edits affect channel organization and user workspace state, but impact is typically scoped to individual users/channels and reversible.
From the tool's definition Tool name 'bookmarks_edit' indicates modification of bookmark data. Description is empty, limiting certainty. Context from sibling tools (manifest_create, manifest_delete, manifest_update) suggests this server enables data mutation across Slack resources.
Attacks that exploit this kind of access
bookmarks_edit. 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 bookmarks_edit: 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.
bookmarks_edit 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 bookmarks_edit 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 bookmarks_edit. 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.
bookmarks_edit 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 →