AI agents call slack_list_dms to retrieve information from Access without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
This is a read-only retrieval operation that queries DM metadata. However, severity is elevated to 'high' because: (1) it exposes all DM conversations accessible to the bot, including potentially sensitive multi-party channels, (2) the server context indicates this is a credential proxy handling OAuth tokens across multiple services, making the DM data a reconnaissance vector for lateral movement or privilege…
From the tool's definition Tool explicitly performs a list operation: 'List all direct message and group DM conversations' with return values 'channel IDs and participant info'. No modification, deletion, or execution described.
Attacks that exploit this kind of access
List all direct message and group DM conversations visible to the bot. Returns channel IDs and participant info. Use this to find DM channel IDs for slack_dm_history. It is categorised as a Read tool in the Access MCP Server, which means it retrieves data without modifying state.
Register the Access MCP server in PolicyLayer and add a rule for slack_list_dms: 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 Access. Nothing to install.
slack_list_dms 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 slack_list_dms 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 slack_list_dms. 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.
slack_list_dms is provided by the Access MCP server (scottpedia0/access). 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 →