AI agents invoke highlight_element to trigger actions in InSite. 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.
Highlighting an element requires executing a browser action (e.g., injecting CSS or JavaScript into the page) to alter its visual appearance. While the effect is transient and non-destructive, it still triggers an external operation on the browser page, placing it in the Execute category. Misuse potential is low since it only affects visual debugging state.
From the tool's definition 'Visually highlight elements on the page' — modifies the visual state of a live browser page by injecting styling or overlays onto elements
Attacks that exploit this kind of access
Visually highlight elements on the page for debugging purposes. It is categorised as a Execute tool in the InSite MCP Server, which means it can trigger actions or run processes. Use rate limits and argument validation.
Register the InSite MCP server in PolicyLayer and add a rule for highlight_element: 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 InSite. Nothing to install.
highlight_element 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 highlight_element 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 highlight_element. 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.
highlight_element is provided by the InSite MCP server (jowharshamshiri/insite). 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 →