Get keystroke data by ID
AI agents call get_keystrokes 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 keystroke data, making it a Read category tool. However, the severity is high because keystroke logs contain highly sensitive information (passwords, PII, credentials, private communications) that could enable further attacks or data exfiltration if obtained by an unauthorized agent.
From the tool's definition Tool name 'get_keystrokes' and description 'Get keystroke data by ID' indicate retrieval of previously captured keystroke logs. This is a read operation that retrieves sensitive data (keystrokes) without modifying or deleting it.
Attacks that exploit this kind of access
Get keystroke data by ID. 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 get_keystrokes: 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.
get_keystrokes 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_keystrokes 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_keystrokes. 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_keystrokes 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 →