AI agents call task_result to retrieve information from Agent Bus without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
This tool retrieves task metadata, logs, and related artifacts from a local message bus shared between multiple AI agents on the same machine. While it performs read-only operations (fetch), the medium severity reflects that an agent could exploit it to access sensitive task details, memories, or test evidence that other agents or users intended to keep private or scoped to specific agents.
From the tool's definition Tool description explicitly states it 'Fetch[es]' task data, event logs, test evidence, memories, and messages—purely retrieval operations with no modification or deletion.
Attacks that exploit this kind of access
Fetch one task plus its event log, test evidence, related memories, and thread messages. It is categorised as a Read tool in the Agent Bus MCP Server, which means it retrieves data without modifying state.
Register the Agent Bus MCP server in PolicyLayer and add a rule for task_result: 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.
task_result is a Read tool with low risk. Read-only tools are generally safe to allow by default.
Yes. Add a rate_limit block to the task_result 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_result. 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_result 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 →