Answer: Auto-review is designed to block actions such as sending private data, secrets, or credentials to untrusted destinations; probing for credentials, tokens, cookies, or session material; broad or persistent security weakening; and destructive actions with significant risk of irreversible damage. The text does not describe what the reviewer sees. Status: Confirmed Entry: tool/codex/permissions-and-security/auto-review-blocked-actions Revision: 1 Digest: sha256:0c6fb8789a468485 (changes whenever the content changes) Timeline: Created: 2026-11-13T03:52:50Z Last changed: 2026-11-13T03:52:50Z Last verified: 2026-11-20T13:41:20Z Next check: 2026-11-21T13:41:20Z Check interval: Daily Expected change: No fixed schedule Data: Field | Value | Source | As of Blocked: private data | sending private data, secrets, or credentials to untrusted destinations | [1] | 2026-11-20 Blocked: credential probing | probing for credentials, tokens, cookies, or session material | [1] | 2026-11-20 Blocked: security weakening | broad or persistent security weakening | [1] | 2026-11-20 Blocked: destructive actions | destructive actions with significant risk of irreversible damage | [1] | 2026-11-20 Sources: [1] OpenAI. "Auto-review". https://learn.chatgpt.com/docs/sandboxing/auto-review.md Role: primary. Accessed: 2026-11-20T13:41:20Z Quote: "sending private data, secrets, or credentials to untrusted destinations" (Supports: Blocked: private data) Quote: "probing for credentials, tokens, cookies, or session material" (Supports: Blocked: credential probing) Quote: "broad or persistent security weakening" (Supports: Blocked: security weakening) Quote: "destructive actions with significant risk of irreversible damage" (Supports: Blocked: destructive actions) Snapshot SHA-256: c9c88533faf92a77bf195cbf82566e5ae2378b7298e0bff23491a09a27839d54 (captured 2026-11-13T03:52:50Z) 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 2026-11-13T03:52:50Z, so the values verified then were kept. Cross-check: not-available at 2026-11-20T13:41:20Z. No independent second source is configured for this entry Last successful check: 2026-11-20T13:41:20Z Last attempt: 2026-11-20T13:41:20Z Notes and limitations: Extracted automatically from a single official source (section "What Auto-review blocks"). Related: https://latestn.com/tool/codex/permissions-and-security/bedrock-authentication How do I authenticate Codex Security scans with Amazon Bedrock? https://latestn.com/tool/codex/permissions-and-security/choose-security-scan-method How do I choose between Daybreak Defense Factory and the Codex Security plugin for scanning code? https://latestn.com/tool/codex/permissions-and-security/ci-severity-policy How do I choose a severity policy for Codex Security findings in CI? https://latestn.com/tool/codex/permissions-and-security/api-key-auth-automation How do I authenticate Codex in automation using an API key? https://latestn.com/tool/codex/permissions-and-security/approval-policies-sandbox-modes How do I configure approval policies and sandbox modes in Codex? https://latestn.com/tool/codex/permissions-and-security/approve-requests-mobile How do I approve Codex action requests from my phone? https://latestn.com/tool/ All entries in AI tools Change log: Time | Event | Change | Source 2026-11-13T03:52:50Z | added | Entry created | — Changes for this entry as a feed: https://latestn.com/tool/codex/permissions-and-security/auto-review-blocked-actions/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/codex/permissions-and-security/auto-review-blocked-actions POST: https://latestn.com/dispute/tool/codex/permissions-and-security/auto-review-blocked-actions with claim, evidence_url, and optionally field and contact (form-encoded or JSON) GET: https://latestn.com/dispute/tool/codex/permissions-and-security/auto-review-blocked-actions?claim={what is wrong}&evidence_url={link} How to cite: LatestN. (2026). What does Codex Auto-review block and what does the reviewer see? Revision 1, last verified 2026-11-20T13:41:20Z. https://latestn.com/tool/codex/permissions-and-security/auto-review-blocked-actions (accessed 2026-11-21T10:07:35Z). @misc{LatestN_tool_codex_permissions_and_security_auto_review_blocked_actions_r1, title = {What does Codex Auto-review block and what does the reviewer see?}, author = {{LatestN}}, year = {2026}, howpublished = {\url{https://latestn.com/tool/codex/permissions-and-security/auto-review-blocked-actions}}, note = {Revision 1; digest sha256:0c6fb8789a468485; last verified 2026-11-20T13:41:20Z; accessed 2026-11-21T10:07:35Z} } 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/codex/permissions-and-security/auto-review-blocked-actions