AI agents call assistant_search_info to retrieve information from Slack without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
This tool retrieves metadata about search capabilities rather than executing searches, modifying data, or performing destructive actions. It is a passive information lookup with no side effects, placing it squarely in the Read category with low severity since it exposes only capability information rather than sensitive user data at scale.
From the tool's definition Tool description states 'Get search capabilities for the team' — a retrieval operation that queries and returns information about available search features without modifying any data.
Attacks that exploit this kind of access
Get search capabilities for the team. It is categorised as a Read tool in the Slack MCP Server, which means it retrieves data without modifying state.
Register the Slack MCP server in PolicyLayer and add a rule for assistant_search_info: 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.
assistant_search_info is a Read tool with low risk. Read-only tools are generally safe to allow by default.
Yes. Add a rate_limit block to the assistant_search_info 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 assistant_search_info. 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.
assistant_search_info 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 →