AI agents invoke a2a_task_cancel to trigger actions in Wmux. What it does depends on the arguments the agent supplies, and its effects often reach beyond the immediate call — builds kicked off, notifications sent, workflows started.
Cancelling a task is an action that triggers an external operation (terminating a running task), which cannot be reversed once cancelled. It falls under Execute as it affects the state of an ongoing operation rather than creating/modifying data or deleting stored data. The impact is medium since cancelling tasks could disrupt ongoing AI agent workflows.
From the tool's definition Cancel a task you previously sent. Only the original sender can cancel.
Attacks that exploit this kind of access
Cancel a task you previously sent. Only the original sender can cancel. It is categorised as a Execute tool in the Wmux MCP Server, which means it can trigger actions or run processes. Use rate limits and argument validation.
Register the Wmux MCP server in PolicyLayer and add a rule for a2a_task_cancel: 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 Wmux. Nothing to install.
a2a_task_cancel is a Execute tool with high risk. Execute tools should be rate-limited and have argument validation enabled.
Yes. Add a rate_limit block to the a2a_task_cancel 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 a2a_task_cancel. 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.
a2a_task_cancel is provided by the Wmux MCP server (openwong2kim/wmux). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.
a2a_task_cancel is one line of Wmux's registry record.
The record carries the whole server: verified identity, auth posture, risk grade, every tool classified, recommended policy — re-checked continuously.
Teams ship this data inside their own products. See what a licence covers →