AI agents call state_screenshot to retrieve information from Ruyipage without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
Screenshots retrieve visual data from the browser with no side effects—they do not modify, execute code, delete data, or move money. This is a Read operation. Severity is medium because screenshots could expose sensitive information displayed on screen (passwords, personal data, proprietary content) if the browser contains such content, posing a privacy/data leakage risk.
From the tool's definition Tool name 'state_screenshot' and context of Firefox browser automation server suggest it captures a visual snapshot of the browser's current state without modifying anything.
Attacks that exploit this kind of access
state_screenshot. It is categorised as a Read tool in the Ruyipage MCP Server, which means it retrieves data without modifying state.
Register the Ruyipage MCP server in PolicyLayer and add a rule for state_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 Ruyipage. Nothing to install.
state_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 state_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 state_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.
state_screenshot is provided by the Ruyipage MCP server (neverl805/ruyipage_mcp). 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 →