Remove a label from a task
AI agents call remove_task_label to permanently remove resources in Vikunja MCP Server — typically in cleanup and lifecycle workflows. It does its job in a single call, and there is no undo.
Removing a label from a task deletes the label-task association. While labels themselves aren't deleted, this action is not easily reversible in an automated context and aligns with destructive removal operations. Severity is medium as it affects metadata/categorization rather than core task data.
From the tool's definition 'Remove a label from a task' — removal of an association (label from task) is typically irreversible without knowing the prior state, and the word 'remove' implies deletion of the relationship.
Attacks that exploit this kind of access
Remove a label from a task. It is categorised as a Destructive tool in the Vikunja MCP Server MCP Server, which means it can permanently delete or destroy data. Block by default and require explicit approval.
Register the Vikunja MCP Server MCP server in PolicyLayer and add a rule for remove_task_label: 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 Vikunja MCP Server. Nothing to install.
remove_task_label 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 remove_task_label 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 remove_task_label. 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.
remove_task_label is provided by the Vikunja MCP Server MCP server (wosh-i/vikunja-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 →