Select all content in the focused widget (ctrl+a).
AI agents invoke select_all to trigger actions in Hermes Computer Use. 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.
This tool executes a keyboard shortcut (Ctrl+A) in a live browser session. While selecting text is nominally benign, it is an active browser automation action that interacts with real OS-level input and can be a step in a larger destructive or exfiltrating workflow (e.g., select-all then copy or delete). It is an Execute-class action due to triggering external browser/OS operations.
From the tool's definition Select all content in the focused widget (ctrl+a) — triggers OS-level keyboard action in a real browser
Risk signalsBulk/mass operation — affects multiple targets
Attacks that exploit this kind of access
Select all content in the focused widget (ctrl+a). It is categorised as a Execute tool in the Hermes Computer Use MCP Server, which means it can trigger actions or run processes. Use rate limits and argument validation.
Register the Hermes Computer Use MCP server in PolicyLayer and add a rule for select_all: 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.
select_all 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 select_all 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 select_all. 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.
select_all 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 →