Cursor has no dangerously skip permissions flag.
Cursor has no --dangerously-skip-permissions; that flag belongs to Claude Code. In the Cursor Agent CLI the bypass is agent --force (aliased --yolo), which force-allows every command unless it is explicitly denied, typically alongside -p/--print and --trust for headless runs. The CLI's command is agent; the older cursor-agent name still works as a legacy alias.
The catch is that deny rules block only the commands they name, so --force effectively means unsupervised shell access. The safer pattern is to keep a human gate on non-allowlisted commands with Pushary, pushing those approvals to your phone and keeping an audit trail.
The flag
agent --force (alias --yolo)Force-allows every command unless it is explicitly denied.
Updated
ظهرنا على Hacker NewsThree ways to run an agent
Full bypass keeps the agent moving but drops the gate. Babysitting keeps the gate but pins you to the keyboard. A phone gate keeps both.
| Approach | Agent keeps moving | Destructive actions gated | Away from the keyboard | Audit trail |
|---|---|---|---|---|
| Full bypass (Cursor) | ||||
| Babysit the terminal | ||||
| Pushary phone gate |
What the flag actually does
The --force flag (aliased --yolo) tells the Cursor Agent CLI to force allow every command unless it is explicitly on the deny list, so the agent runs terminal commands and edits with no confirmation prompt. In headless and scripted use it is usually paired with -p/--print (non-interactive output, full tool access including write and shell), --approve-mcps (auto-approve all MCP servers), and --trust (trust the workspace without prompting in headless mode).
Together these give a fully unattended agent that executes on its own.
Cursor keeps asking for permission: check these first
First identify the surface: Cursor Agent CLI and the Cursor editor have different settings. Changing a CLI configuration file does not establish the editor's approval behavior.
For the CLI, inspect ~/.cursor/cli-config.json and the project's .cursor/cli.json. Check permissions.allow and permissions.deny against the exact command or file being requested. Deny rules take precedence. Shell(git) covers any git subcommand, so use a narrower command:args pattern when you only intend to allow a specific operation.
Workspace trust, MCP server approval and permission to run a command are separate checks. --trust and --approve-mcps do not mean you approved every future shell action. In the editor, check the run mode under Settings > Agents > Approvals & Execution (Auto-review, Allowlist or Run Everything) and any team restrictions on the actual request.
If you want to leave the desk while retaining a decision on risky commands, use the supported Pushary Cursor hooks. If a request is missing or stale, check Cursor's session first; another notification channel cannot repair its host UI.
Why people use it, and the real risk
With --force, Cursor's deny rules are the only permission check left, and they block only the commands they name. In 2025, security researchers at Backslash got past the editor's old Auto-Run denylist with tricks such as Base64-encoded commands, and Cursor removed that denylist in version 1.3 in favor of allowlists. A list of what not to run is not a reliable fence. In this mode the agent runs shell commands and file edits with no human check, so a destructive command or a prompt-injection payload hidden in a repo file or fetched web page executes immediately.
Because MCP servers are auto-approved with --approve-mcps, a malicious or compromised server also runs unattended. There is no per-command approval record, so you cannot later show which actions a human sanctioned.
The safer alternative
Keep permissions scoped to the commands and files you intend to allow. The Pushary Cursor plugin can hold supported shell commands for your phone approval through Cursor hooks. Plain MCP gives the agent tools for questions and notifications; it does not enforce a gate.
Neither path overrides a Cursor denial or guarantees coverage of every editor action. Check the integration guide before relying on an approval boundary.
Cursor skip permissions questions
Does Cursor have --dangerously-skip-permissions?
No. It is a Claude Code flag. The Cursor equivalent is agent --force in the Cursor Agent CLI, aliased --yolo, which force-allows every command unless it is explicitly denied. Headless runs usually pair it with -p/--print, --trust to skip the workspace trust prompt, and --approve-mcps to auto-approve MCP servers. --force still honors your deny rules, and everything else runs with no prompt.
How do I enable YOLO mode in Cursor CLI?
In the Cursor Agent CLI, whose command is agent (formerly cursor-agent), the flag is --force (its alias is --yolo), described in Cursor's docs as force allow commands unless explicitly denied. For headless automation you usually add -p/--print for non-interactive output and --trust to skip the workspace trust prompt, and --approve-mcps to auto-approve MCP servers. Because anything you have not denied runs unprompted, a safer route is to allowlist safe commands and push everything else to your phone with Pushary.
How do I make Cursor agent auto-run terminal commands without asking?
Passing --force makes the Cursor Agent CLI auto-run commands that are not on the deny list. In the editor, the matching setting is the Run Everything run mode, the no-prompt option in the setting Cursor once called Auto-Run, and before that YOLO mode. You set it under Settings > Agents > Approvals & Execution, and it runs every tool call without the sandbox or Auto-review. On the CLI, a deny list blocks only what it names, so it is not a strong guardrail. Keep a human in the loop on risky commands with a Pushary policy that sends the approval to your phone and logs the decision.
Is Cursor --force safe to run unattended?
Only inside an isolated sandbox or disposable container, never against a repo with live credentials or production access, because with --force the agent can run any destructive or injected command your deny rules do not name, with no human check. For real work, keep an allowlist for safe commands and gate the rest through Pushary so approvals hit your phone and stay in an audit trail.
Run Cursor unattended without skipping every permission.
Keep the agent moving, gate the risky calls, approve from your phone. Set up in two minutes.
Start your trial$9.99/mo after a 3-day free trial. Cancel anytime.