Critical-risk tools in Ai Agent

Critical severity Ai Agent MCP Server 1 of 8 tools

1 of the 8 tools in Ai Agent are classified as critical risk. This page profiles those tools specifically, with recommended policy actions and the attack patterns that target them.

Every operation listed below is an action PolicyLayer recommends controlling at the transport layer. Open any tool to see the full profile, risk score, and YAML policy snippet.

Tools at critical risk

uninstall_resource Destructive

Uninstall a resource from the user's local machine. Command/Skill resources: unregisters MCP Prompt from memory and queues local script directory deletion. Rule resources: retur...

Attacks that target this class

Critical-risk tools in any server share these documented attack patterns. Each links to the full case and the defensive policy.

Destructive Action Autonomy
Privilege escalation via admin-only tools
Data exfiltration via tool chaining
Runaway Tool Loops

Critical-risk tools in Ai Agent

Tools at critical risk

Attacks that target this class

More on Ai Agent

Let agents act without letting them run wild.