Take a screenshot on a beacon
AI agents invoke spawn_screenshot to trigger actions in Cobalt Strike MCP Server. 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.
Taking a screenshot executes an action on a remote compromised system, capturing potentially sensitive information from the target's screen. This is a red team surveillance operation that runs on a beacon (remote agent), making it Execute category. The blast radius is high as it can exfiltrate sensitive data from compromised systems without the target's knowledge.
From the tool's definition 'Take a screenshot on a beacon' — triggers an external operation on a remote beacon (compromised host) to capture screen contents
Attacks that exploit this kind of access
Take a screenshot on a beacon. It is categorised as a Execute tool in the Cobalt Strike MCP Server MCP Server, which means it can trigger actions or run processes. Use rate limits and argument validation.
Register the Cobalt Strike MCP Server MCP server in PolicyLayer and add a rule for spawn_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 Cobalt Strike MCP Server. Nothing to install.
spawn_screenshot 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 spawn_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 spawn_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.
spawn_screenshot is provided by the Cobalt Strike MCP Server MCP server (mickeydb/cobalt-strike-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 →