This record as markdown: /tools/aws/detach-user-policy.md
What detach_user_policy does on AWS
AI agents call detach_user_policy to permanently remove resources in AWS, typically in cleanup and lifecycle workflows. It does its job in a single call, and there is no undo.
Why detach_user_policy is rated Critical
Detaching a policy from an IAM user removes permissions granted by that policy. While the policy itself is not deleted, the detachment action removes the binding and could immediately revoke access for the user, which can be considered irreversible in its immediate effect and has high security blast radius.
From the tool's definition Tool name: 'detach_user_policy' — 'detach' implies removing an attached IAM policy from a user, which is an irreversible removal of an access control association.
Attacks that exploit this kind of access
The rule that runs detach_user_policy safely
PolicyLayer is an MCP gateway: it sits between your AI agents and AWS, and checks every tool call against a rule you set before the call runs. Nothing changes on the server itself. For detach_user_policy, this is the rule to start with:
detach_user_policy is removed from the agent's tool list entirely, so the agent never calls it. The rest of the server keeps working.
The button opens the PolicyLayer dashboard: create your workspace, connect AWS, apply this rule, and every detach_user_policy call is checked against it from then on.
Questions about detach_user_policy
detach_user_policy is a destructive tool on the AWS MCP server. It is categorised as a Destructive tool in the AWS MCP Server, which means it can permanently delete or destroy data. Block by default and require explicit approval.
Register the AWS MCP server in PolicyLayer and add a rule for detach_user_policy: 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 AWS. Nothing to install.
detach_user_policy 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 detach_user_policy 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 detach_user_policy. 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.
detach_user_policy is provided by the AWS MCP server (@awslabs/mcp). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.
More on AWS, and thousands of servers like it.
Across the catalogue