AI agents call verify_task_run_artifacts to retrieve information from Todos without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
This is a read operation that inspects existing data (run artifacts and their checksums) to validate integrity. It has no side effects, creates no new data, executes no external commands, and cannot delete or modify anything. The blast radius of misuse is minimal—worst case an incorrect verification result could mislead but cannot corrupt data or trigger external operations.
From the tool's definition Tool performs verification by comparing stored artifact content against recorded checksums. The verb 'verify' and the action of checking content against checksums are read-only operations that retrieve and compare data without modifying or deleting anything.
Attacks that exploit this kind of access
Verify locally stored run artifact content against recorded checksums. It is categorised as a Read tool in the Todos MCP Server, which means it retrieves data without modifying state.
Register the Todos MCP server in PolicyLayer and add a rule for verify_task_run_artifacts: 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.
verify_task_run_artifacts 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 verify_task_run_artifacts 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 verify_task_run_artifacts. 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.
verify_task_run_artifacts 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 →