Fill an input field
AI agents use fill to create or update resources in Chromium ARM64 Browser — usually the action step of a workflow, after the agent has gathered context. Every call changes real data in your Chromium ARM64 Browser environment.
Filling input fields is a reversible write operation that modifies form data without deletion. Severity is medium because while the tool itself is non-destructive, an AI agent could misuse it to inject malicious data, fill sensitive fields, or populate forms with unintended values in critical applications. The capability poses moderate risk in unsupervised automation scenarios.
From the tool's definition The tool description states it will "Fill an input field", which creates or modifies data in web forms. The sibling tools (click, evaluate, get_cookies, etc.) confirm this is a browser automation context where form manipulation occurs.
Attacks that exploit this kind of access
Fill an input field. It is categorised as a Write tool in the Chromium ARM64 Browser MCP Server, which means it can create or modify data. Consider rate limits to prevent runaway writes.
Register the Chromium ARM64 Browser MCP server in PolicyLayer and add a rule for fill: 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 Chromium ARM64 Browser. Nothing to install.
fill 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 fill 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 fill. 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.
fill is provided by the Chromium ARM64 Browser MCP server (nfodor/mcp-chromium-arm64). 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 →