AI agents use task_create to create or update resources in AgentOS — usually the action step of a workflow, after the agent has gathered context. Every call changes real data in your AgentOS environment.
This tool creates new task records in a state management system, which is a reversible write operation. It does not execute arbitrary code, delete data, move funds, or trigger external operations—it simply initializes task metadata. The severity is low because task creation has minimal blast radius; erroneous tasks can be managed or ignored without significant harm.
From the tool's definition Tool name 'task_create' and description 'Create a new task with initial state' indicate creation of new data structures for task tracking.
Attacks that exploit this kind of access
Create a new task with initial state for tracking progress across sessions. It is categorised as a Write tool in the AgentOS MCP Server, which means it can create or modify data. Consider rate limits to prevent runaway writes.
Register the AgentOS MCP server in PolicyLayer and add a rule for task_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 AgentOS. Nothing to install.
task_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 task_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 task_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.
task_create is provided by the AgentOS MCP server (netflypsb/agentos). 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 →