High-risk tools in Vscode
6 of the 24 tools in Vscode are classified as high risk. This page profiles those tools specifically, with recommended policy actions and the attack patterns that target them.
Every operation listed below is an action PolicyLayer recommends controlling at the transport layer. Open any tool to see the full profile, risk score, and YAML policy snippet.
Tools at high risk
-
cursor_open_chatExecuteOpen a new chat, composer, or agent panel in Cursor.
-
cursor_open_model_pickerExecuteOpen the model selector UI in Cursor so the user can pick a model visually.
-
cursor_run_commandExecuteExecute any VS Code / Cursor command by its ID. Use cursor_list_commands to discover IDs.
-
cursor_send_and_waitExecuteSend a message to the current Cursor agent chat and wait (blocking) until Cursor finishes responding. Returns the full response text. Use since_ms from cursor_open_chat to scope...
-
cursor_send_messageExecuteOpen the Cursor chat and send a message (starts a new conversation).
-
run_commandExecuteExecute a shell command in the given working directory. Returns stdout, stderr, and exit code.
Attacks that target this class
High-risk tools in any server share these documented attack patterns. Each links to the full case and the defensive policy.