AI agents use vikunja_add_label_to_task to create or update resources in Vikunja — usually the action step of a workflow, after the agent has gathered context. Every call changes real data in your Vikunja environment.
This tool creates a new relationship between a task and an existing label. It modifies task state (the label assignment) but does not create, delete, or destroy data—the change can be undone by removing the label. This is a typical Write operation: it updates data reversibly. Severity is medium because mislabeling tasks could cause workflow confusion and incorrect task categorization, but the impact is recoverable.
From the tool's definition Tool description states "Attach an existing label to a task" — this modifies task metadata by adding a label association, which is a reversible data mutation.
Attacks that exploit this kind of access
Attach an existing label to a task. It is categorised as a Write tool in the Vikunja MCP Server, which means it can create or modify data. Consider rate limits to prevent runaway writes.
Register the Vikunja MCP server in PolicyLayer and add a rule for vikunja_add_label_to_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 Vikunja. Nothing to install.
vikunja_add_label_to_task 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 vikunja_add_label_to_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 vikunja_add_label_to_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.
vikunja_add_label_to_task is provided by the Vikunja MCP server (shichao402/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 →