AI agents use apply_failure_triage to create or update resources in Todos — usually the action step of a workflow, after the agent has gathered context. Every call changes real data in your Todos environment.
This is a Write operation because it creates or modifies task/run data (annotations, status changes, task splits) without irreversible deletion. The actions are primarily metadata updates and state transitions. It does not execute arbitrary code or delete data permanently, so it is not Execute or Destructive.
From the tool's definition The tool applies triage actions that include 'annotate, retry, reopen, split, or escalate' on a failed task/run. These actions modify task state and metadata reversibly (adding annotations, changing task status, splitting tasks).
Attacks that exploit this kind of access
Apply triage action: annotate, retry, reopen, split, or escalate on a failed task/run. It is categorised as a Write tool in the Todos MCP Server, which means it can create or modify data. Consider rate limits to prevent runaway writes.
Register the Todos MCP server in PolicyLayer and add a rule for apply_failure_triage: 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 Todos. Nothing to install.
apply_failure_triage 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 apply_failure_triage 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 apply_failure_triage. 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.
apply_failure_triage is provided by the Todos MCP server (@hasna/todos). 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 →