Download a file from a beacon
AI agents call beacon_download_file to retrieve information from Cobalt Strike MCP Server without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
This tool retrieves file contents from a compromised system (beacon) and transfers them to the operator. While categorically a Read operation (no side effects on the target), the severity is high because: (1) it operates within an active red team/adversarial framework (Cobalt Strike), (2) it enables exfiltration of sensitive data from compromised hosts, and (3) misuse could lead to unauthorized access to…
From the tool's definition Tool name: 'beacon_download_file'; description: 'Download a file from a beacon' — performs data retrieval with no modification or deletion.
Attacks that exploit this kind of access
Download a file from a beacon. It is categorised as a Read tool in the Cobalt Strike MCP Server MCP Server, which means it retrieves data without modifying state.
Register the Cobalt Strike MCP Server MCP server in PolicyLayer and add a rule for beacon_download_file: 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.
beacon_download_file 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 beacon_download_file 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 beacon_download_file. 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.
beacon_download_file 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 →