Answer: Enterprise teams can configure Run Mode policies in the team dashboard, where end users choose between Auto-review (the default), Allowlist, and Run Everything modes; you can also create an allowlist of commands that don't require approval. The allowlist is best-effort, not a security boundary, so it should be combined with other security controls like hooks. Status: Confirmed Entry: tool/cursor/permissions-and-security/restrict-terminal-commands Revision: 1 Digest: sha256:57c8d257e2d47100 (changes whenever the content changes) Timeline: Created: 2026-11-13T03:10:32Z Last changed: 2026-11-13T03:10:32Z Last verified: 2026-11-20T12:37:35Z Next check: 2026-11-21T12:37:35Z Check interval: Daily Expected change: No fixed schedule Data: Field | Value | Source | As of Configuration location | team dashboard | [1] | 2026-11-20 Minimum version | Cursor 3.6 and above | [1] | 2026-11-20 Default mode | Auto-review | [1] | 2026-11-20 Available modes | Allowlist | [1] | 2026-11-20 Allowlist examples | npm install | [1] | 2026-11-20 Allowlist limitation | best-effort, not a security boundary | [1] | 2026-11-20 Sources: [1] Anysphere. "cursor.com/docs/enterprise/llm-safety-and-controls.md". https://cursor.com/docs/enterprise/llm-safety-and-controls.md Role: primary. Accessed: 2026-11-20T12:37:35Z Quote: "Enterprise teams can configure Run Mode policies in the team dashboard." (Supports: Configuration location) Quote: "In Cursor 3.6 and above, end users choose between **Auto-review** (the default), **Allowlist**, and **Run Everything** modes." (Supports: Minimum version) Quote: "**Auto-review** (the default)" (Supports: Default mode) Quote: "**Allowlist**, and **Run Everything** modes" (Supports: Available modes) Quote: "You can create an allowlist of commands that don't require approval, such as `npm install`, `pip install`, `cargo build`, or `make test`." (Supports: Allowlist examples) Quote: "The allowlist is best-effort, not a security boundary." (Supports: Allowlist limitation) Snapshot SHA-256: 4a4d4bd68097abc882ba1dafe86fa37022f986b74b5520afe58b6dba0839f894 (captured 2026-11-13T03:10:32Z) Verification: Method: Automated extraction from [1] with deepseek-flash (JSON output, thinking disabled). Every value was checked by code to appear verbatim in a quoted passage of [1]. On this check the text of [1] was unchanged since 2026-11-13T03:10:32Z, so the values verified then were kept. Cross-check: not-available at 2026-11-20T12:37:35Z. No independent second source is configured for this entry Last successful check: 2026-11-20T12:37:35Z Last attempt: 2026-11-20T12:37:35Z Notes and limitations: Extracted automatically from a single official source (section "Terminal command restrictions"). Related: https://latestn.com/tool/cursor/permissions-and-security/revoke-project-repo-access How do I remove or revoke a Cursor Project's access to a repository or environment? https://latestn.com/tool/cursor/permissions-and-security/revoke-user-token How do I revoke an installation user token in Cursor Origin? https://latestn.com/tool/cursor/permissions-and-security/rotate-service-account-api-key How do I rotate an API key for a Cursor service account? https://latestn.com/tool/cursor/permissions-and-security/request-user-tokens-scope How do I request the namespace:user_tokens:write scope for a Cursor Origin app installation? https://latestn.com/tool/cursor/permissions-and-security/restrict-cloud-agent-repositories How do I restrict which repositories Cursor Cloud Agents can reach? https://latestn.com/tool/cursor/permissions-and-security/restrict-invites-domains How do I restrict invites to verified domains in Cursor Teams? https://latestn.com/tool/ All entries in AI tools Change log: Time | Event | Change | Source 2026-11-13T03:10:32Z | added | Entry created | — Changes for this entry as a feed: https://latestn.com/tool/cursor/permissions-and-security/restrict-terminal-commands/latest Challenge this entry: Open challenges: None How: If a value here is wrong or out of date, send what is wrong and a link to evidence. Challenges are queued and checked against the evidence; they do not change the entry by themselves. If the entry changes as a result, the change log says so. Form: https://latestn.com/dispute/tool/cursor/permissions-and-security/restrict-terminal-commands POST: https://latestn.com/dispute/tool/cursor/permissions-and-security/restrict-terminal-commands with claim, evidence_url, and optionally field and contact (form-encoded or JSON) GET: https://latestn.com/dispute/tool/cursor/permissions-and-security/restrict-terminal-commands?claim={what is wrong}&evidence_url={link} How to cite: LatestN. (2026). How do I restrict which terminal commands Cursor agents can run? Revision 1, last verified 2026-11-20T12:37:35Z. https://latestn.com/tool/cursor/permissions-and-security/restrict-terminal-commands (accessed 2026-11-21T10:06:38Z). @misc{LatestN_tool_cursor_permissions_and_security_restrict_terminal_commands_r1, title = {How do I restrict which terminal commands Cursor agents can run?}, author = {{LatestN}}, year = {2026}, howpublished = {\url{https://latestn.com/tool/cursor/permissions-and-security/restrict-terminal-commands}}, note = {Revision 1; digest sha256:57c8d257e2d47100; last verified 2026-11-20T12:37:35Z; accessed 2026-11-21T10:06:38Z} } Reuse: License: CC BY 4.0 (https://creativecommons.org/licenses/by/4.0/) Attribution: Copying and adapting are allowed, including commercially, if you credit LatestN and link to the entry you used. Each entry ends with a ready-made citation. URL: https://latestn.com/tool/cursor/permissions-and-security/restrict-terminal-commands