Poll until the selector matches at least one visible element, or
AI agents invoke dom_wait to trigger actions in Hermes Computer Use. What it does depends on the arguments the agent supplies, and its effects often reach beyond the immediate call — builds kicked off, notifications sent, workflows started.
dom_wait executes a polling operation that waits for page state changes and can trigger subsequent actions. While not destructive by itself, it is a control-flow tool that orchestrates browser automation—a form of code execution with real-world effects on a live browser.
From the tool's definition "Poll until the selector matches at least one visible element" indicates active browser manipulation and conditional execution based on DOM state.
Attacks that exploit this kind of access
Poll until the selector matches at least one visible element, or. It is categorised as a Execute tool in the Hermes Computer Use MCP Server, which means it can trigger actions or run processes. Use rate limits and argument validation.
Register the Hermes Computer Use MCP server in PolicyLayer and add a rule for dom_wait: 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 Hermes Computer Use. Nothing to install.
dom_wait is a Execute tool with high risk. Execute tools should be rate-limited and have argument validation enabled.
Yes. Add a rate_limit block to the dom_wait 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 dom_wait. 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.
dom_wait is provided by the Hermes Computer Use MCP server (noah3521/hermes-computer-use). 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 →