Delete a task by ID. This permanently removes the task and its history. Cannot be undone.
AI agents call bytebot_delete_task to permanently remove resources in ByteBot MCP Server — typically in cleanup and lifecycle workflows. It does its job in a single call, and there is no undo.
This tool irreversibly deletes data (task records and history) with no recovery mechanism. While the blast radius is limited to task metadata rather than critical system data or financial assets, the permanent nature of deletion without undo capability makes it Destructive.
From the tool's definition Tool description explicitly states: 'permanently removes the task and its history. Cannot be undone.' The term 'permanently' and 'cannot be undone' directly indicate irreversible deletion.
Attacks that exploit this kind of access
Delete a task by ID. This permanently removes the task and its history. Cannot be undone. It is categorised as a Destructive tool in the ByteBot MCP Server MCP Server, which means it can permanently delete or destroy data. Block by default and require explicit approval.
Register the ByteBot MCP Server MCP server in PolicyLayer and add a rule for bytebot_delete_task: 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 ByteBot MCP Server. Nothing to install.
bytebot_delete_task 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 bytebot_delete_task 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 bytebot_delete_task. 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.
bytebot_delete_task is provided by the ByteBot MCP Server MCP server (sensuslab/spark-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 →