AI agents call browser_screenshot to retrieve information from Byob without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
Screenshots are passive observations of content. While saving to disk involves file I/O, the action does not modify, delete, or execute code on remote systems. It falls squarely within Read category (retrieves data with no side effects).
From the tool's definition Tool description states it "Capture[s] a screenshot of a webpage and save[s] it to disk" with no modification of webpage state or external data. The action is read-only—it retrieves the visual representation of a page without side effects.
Attacks that exploit this kind of access
Capture a screenshot of a webpage and save it to disk. Returns the file PATH. It is categorised as a Read tool in the Byob MCP Server, which means it retrieves data without modifying state.
Register the Byob MCP server in PolicyLayer and add a rule for browser_screenshot: 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 Byob. Nothing to install.
browser_screenshot 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 browser_screenshot 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 browser_screenshot. 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.
browser_screenshot is provided by the Byob MCP server (wxtsky/byob). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.