AI agents call get_screenshot to retrieve information from Instruckt without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
This tool retrieves an existing screenshot image associated with an annotation. It is a query operation that reads data without modifying, deleting, or executing anything. The blast radius of misuse is minimal — an agent could retrieve screenshots it shouldn't access, but no data would be altered or operations triggered. Classified as Read with low severity.
From the tool's definition Tool name is 'get_screenshot' and description states 'Get the screenshot image for a specific annotation by ID' — purely retrieves/queries data with no side effects.
Attacks that exploit this kind of access
Get the screenshot image for a specific annotation by ID. It is categorised as a Read tool in the Instruckt MCP Server, which means it retrieves data without modifying state.
Register the Instruckt MCP server in PolicyLayer and add a rule for get_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 Instruckt. Nothing to install.
get_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 get_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 get_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.
get_screenshot is provided by the Instruckt MCP server (tdwesten/instruckt-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 →