Answer: Scheduled tasks run unattended and use your default sandbox settings, with behavior depending on whether the sandbox mode is read-only, workspace-write, or full access. Scheduled tasks use `approval_policy = "never"` when your organization policy allows it, and fall back to the approval behavior of your selected permission mode if admin requirements disallow it. Status: Confirmed Entry: tool/chatgpt/permissions-and-security/scheduled-tasks-permissions Revision: 1 Digest: sha256:e5b65569fb38bf90 (changes whenever the content changes) Timeline: Created: 2026-11-13T03:47:41Z Last changed: 2026-11-13T03:47:41Z Last verified: 2026-11-20T13:35:17Z Next check: 2026-11-21T13:35:17Z Check interval: Daily Expected change: No fixed schedule Data: Field | Value | Source | As of default behavior | Scheduled tasks run unattended and use your default sandbox settings. | [1] | 2026-11-20 read-only mode | read-only | [1] | 2026-11-20 workspace-write mode | workspace-write | [1] | 2026-11-20 full access mode | full access | [1] | 2026-11-20 approval policy | approval_policy = "never" | [1] | 2026-11-20 fallback behavior | scheduled tasks fall back to the approval behavior of your selected permission | [1] | 2026-11-20 Sources: [1] OpenAI. "Scheduled tasks". https://learn.chatgpt.com/docs/automations.md Role: primary. Accessed: 2026-11-20T13:35:17Z Quote: "Scheduled tasks run unattended and use your default sandbox settings." (Supports: default behavior) Quote: "If your sandbox mode is **read-only**, tool calls fail if they require" (Supports: read-only mode) Quote: "If your sandbox mode is **workspace-write**, tool calls fail if they require" (Supports: workspace-write mode) Quote: "If your sandbox mode is **full access**, background scheduled tasks carry" (Supports: full access mode) Quote: "Scheduled tasks use `approval_policy = "never"` when your organization policy" (Supports: approval policy) Quote: "scheduled tasks fall back to the approval behavior of your selected permission" (Supports: fallback behavior) Snapshot SHA-256: cd6ad46c3c8304a56fa64657492ce2585afda5212ba3fe0562d59cc9be9596db (captured 2026-11-13T03:47:39Z) 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 2026-11-13T03:47:41Z, so the values verified then were kept. Cross-check: not-available at 2026-11-20T13:35:17Z. No independent second source is configured for this entry Last successful check: 2026-11-20T13:35:17Z Last attempt: 2026-11-20T13:35:17Z Notes and limitations: Extracted automatically from a single official source (section "Permissions and security model"). Related: https://latestn.com/tool/chatgpt/permissions-and-security/secure-account-suspicious-activity How do I secure my ChatGPT account if I suspect suspicious activity? https://latestn.com/tool/chatgpt/permissions-and-security/send-client-certificates How do I send client certificates with my OpenAI API request? https://latestn.com/tool/chatgpt/permissions-and-security/set-default-app-permission How do I set the default permission for apps in ChatGPT? https://latestn.com/tool/chatgpt/permissions-and-security/rotate-api-key How do I rotate my OpenAI API key if it's compromised? https://latestn.com/tool/chatgpt/permissions-and-security/rotate-revoke-api-key How do I rotate or revoke an exposed OpenAI API key? https://latestn.com/tool/chatgpt/permissions-and-security/safety-check-not-policy-violation Do ChatGPT's additional safety checks mean I violated OpenAI's Usage Policies? https://latestn.com/tool/ All entries in AI tools Change log: Time | Event | Change | Source 2026-11-13T03:47:41Z | added | Entry created | — Changes for this entry as a feed: https://latestn.com/tool/chatgpt/permissions-and-security/scheduled-tasks-permissions/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/chatgpt/permissions-and-security/scheduled-tasks-permissions POST: https://latestn.com/dispute/tool/chatgpt/permissions-and-security/scheduled-tasks-permissions with claim, evidence_url, and optionally field and contact (form-encoded or JSON) GET: https://latestn.com/dispute/tool/chatgpt/permissions-and-security/scheduled-tasks-permissions?claim={what is wrong}&evidence_url={link} How to cite: LatestN. (2026). What permissions and security model apply to ChatGPT scheduled tasks? Revision 1, last verified 2026-11-20T13:35:17Z. https://latestn.com/tool/chatgpt/permissions-and-security/scheduled-tasks-permissions (accessed 2026-11-21T10:05:00Z). @misc{LatestN_tool_chatgpt_permissions_and_security_scheduled_tasks_permissions_r1, title = {What permissions and security model apply to ChatGPT scheduled tasks?}, author = {{LatestN}}, year = {2026}, howpublished = {\url{https://latestn.com/tool/chatgpt/permissions-and-security/scheduled-tasks-permissions}}, note = {Revision 1; digest sha256:e5b65569fb38bf90; last verified 2026-11-20T13:35:17Z; accessed 2026-11-21T10:05:00Z} } 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/chatgpt/permissions-and-security/scheduled-tasks-permissions