AI agents use submit_review to create or update resources in Agent Bus — usually the action step of a workflow, after the agent has gathered context. Every call changes real data in your Agent Bus environment.
The tool creates or updates review records that affect task workflow state (approved/rejected/changes_requested), which is reversible data modification. It does not delete data (Destructive), execute arbitrary code (Execute), move money (Financial), or merely read data (Read).
From the tool's definition Tool description states 'Submit verifier review for a task. Approved reviews satisfy review gates; rejected reviews mark changes_requested.' This modifies task state by updating review status and gating decisions.
Attacks that exploit this kind of access
Submit verifier review for a task. Approved reviews satisfy review gates; rejected reviews mark changes_requested. It is categorised as a Write tool in the Agent Bus MCP Server, which means it can create or modify data. Consider rate limits to prevent runaway writes.
Register the Agent Bus MCP server in PolicyLayer and add a rule for submit_review: 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 Agent Bus. Nothing to install.
submit_review 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 submit_review 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 submit_review. 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.
submit_review is provided by the Agent Bus MCP server (mustaphasteph/agent-bus). 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 →