AI agents use apps_manifest_create 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 creates a new app in Slack, which is a reversible write operation. While it doesn't delete data (which would be Destructive) or execute arbitrary code (which would be Execute), it does create a significant new resource that could be used for malicious purposes like data exfiltration, phishing, or unauthorized monitoring if an AI agent were compromised.
From the tool's definition Tool name 'apps_manifest_create' and description 'Create an app from an app manifest' indicate creation of a new application resource in Slack. This is a write operation that modifies the Slack workspace by adding a new app.
Attacks that exploit this kind of access
Create an app from an app manifest. 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 apps_manifest_create: 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.
apps_manifest_create 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 apps_manifest_create 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 apps_manifest_create. 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.
apps_manifest_create 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 →