AI agents use task_update to create or update resources in Outpost — usually the action step of a workflow, after the agent has gathered context. Every call changes real data in your Outpost environment.
The 'update' operation creates or modifies data reversibly, fitting the Write category. Severity is medium because task modification could affect workflows and reminders, but is reversible (data can be modified again or restored). Confidence is 0.85 rather than higher due to empty description, though the naming pattern and server context provide strong contextual evidence.
From the tool's definition Tool name is 'task_update' on an Outlook Tasks service. The name and context (Microsoft Graph API for Tasks) indicate modification of existing task data.
Attacks that exploit this kind of access
task_update. It is categorised as a Write tool in the Outpost MCP Server, which means it can create or modify data. Consider rate limits to prevent runaway writes.
Register the Outpost MCP server in PolicyLayer and add a rule for task_update: 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 Outpost. Nothing to install.
task_update 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_update 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_update. 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_update is provided by the Outpost MCP server (signalclaude/outpost). 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 →