stars_remove
AI agents call stars_remove to permanently remove resources in Slack — typically in cleanup and lifecycle workflows. It does its job in a single call, and there is no undo.
Based on the tool name, 'stars_remove' likely removes a star (bookmark/saved item) from a Slack message or file. Removal of a saved item is a destructive action (irreversible deletion of the star association). However, because the description is empty, confidence is reduced. Severity is medium as losing a star/bookmark has limited blast radius but could affect user workflows.
From the tool's definition Tool name 'stars_remove' suggests removal of a star/bookmark; description is empty and uninformative, lowering confidence.
Attacks that exploit this kind of access
stars_remove. It is categorised as a Destructive tool in the Slack MCP Server, which means it can permanently delete or destroy data. Block by default and require explicit approval.
Register the Slack MCP server in PolicyLayer and add a rule for stars_remove: 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.
stars_remove is a Destructive tool with critical risk. Critical-risk tools should be blocked by default and only enabled with explicit human approval.
Yes. Add a rate_limit block to the stars_remove 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 stars_remove. 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.
stars_remove 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 →