Copy the current selection to clipboard (ctrl+c).
AI agents use copy to create or update resources in Hermes Computer Use — usually the action step of a workflow, after the agent has gathered context. Every call changes real data in your Hermes Computer Use environment.
The tool writes to the clipboard, a system resource, making it a Write action. Severity is medium because while it can capture sensitive data from the screen (credentials, PII), it doesn't directly exfiltrate data or cause irreversible harm on its own—it merely stages data for potential extraction.
From the tool's definition Tool copies current selection to clipboard via ctrl+c, which writes data to the clipboard without permanent modifications or data deletion.
Attacks that exploit this kind of access
Copy the current selection to clipboard (ctrl+c). It is categorised as a Write tool in the Hermes Computer Use MCP Server, which means it can create or modify data. Consider rate limits to prevent runaway writes.
Register the Hermes Computer Use MCP server in PolicyLayer and add a rule for copy: 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 Hermes Computer Use. Nothing to install.
copy is a Write tool with medium risk. Write tools should be rate-limited to prevent accidental bulk modifications.
Yes. Add a rate_limit block to the copy 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 copy. 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.
copy is provided by the Hermes Computer Use MCP server (noah3521/hermes-computer-use). 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 →