Answer: To start a deep security scan, open **Security** > **Scans** and select **+ Scan**, then choose a repository or folder, select **Codebase**, and turn on **Deep scan**. You can also start it from a Codex conversation using `$codex-security:deep-security-scan`. Status: Confirmed Entry: tool/codex/permissions-and-security/start-deep-security-scan Revision: 2 Digest: sha256:b8ef579270e5e213 (changes whenever the content changes) Timeline: Created: 2026-11-13T03:53:27Z Last changed: 2026-11-20T13:42:00Z (Recommended reasoning effort: — → xhigh) Last verified: 2026-11-20T13:42:00Z Next check: 2026-11-21T13:42:00Z Check interval: Daily Expected change: No fixed schedule Data: Field | Value | Source | As of Navigation path | Security | [1] | 2026-11-20 Scan type option | Codebase | [1] | 2026-11-20 Deep scan toggle | Deep scan | [1] | 2026-11-20 Final action | Start scan | [1] | 2026-11-20 Conversation command | $codex-security:deep-security-scan | [1] | 2026-11-20 Recommended model | gpt-5.6-sol | [1] | 2026-11-20 Recommended reasoning effort | xhigh | [1] | 2026-11-20 Sources: [1] OpenAI. "Run a deep security scan". https://learn.chatgpt.com/docs/security/plugin/deep-scans.md Role: primary. Accessed: 2026-11-20T13:42:00Z Quote: "Open **Security** > **Scans** and select **+ Scan**." (Supports: Navigation path) Quote: "Choose a repository or folder, select **Codebase**, and turn on **Deep scan**." (Supports: Scan type option) Quote: "select **Codebase**, and turn on **Deep scan**." (Supports: Deep scan toggle) Quote: "Select **Start scan**." (Supports: Final action) Quote: "Use $codex-security:deep-security-scan to run a deep security scan of this repository." (Supports: Conversation command) Quote: "For the best scan quality, use `gpt-5.6-sol`" (Supports: Recommended model) Quote: "with `xhigh` reasoning effort." (Supports: Recommended reasoning effort) Snapshot SHA-256: 4b0062f844a5f0836d57bd1b8975dfe0e2383c660ad08a78d695b1f65ebc5f77 (captured 2026-11-19T13:32:16Z) 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 2026-11-19T13:32:16Z, so the values verified then were kept. Cross-check: not-available at 2026-11-20T13:42:00Z. No independent second source is configured for this entry Last successful check: 2026-11-20T13:42:00Z Last attempt: 2026-11-20T13:42:00Z Notes and limitations: Extracted automatically from a single official source (section "Start the deep scan"). Related: https://latestn.com/tool/codex/permissions-and-security/start-scan-from-conversation How do I start a security scan from a conversation in Codex? https://latestn.com/tool/codex/permissions-and-security/start-security-scan How do I start a security scan in the Codex Security workbench? https://latestn.com/tool/codex/permissions-and-security/test-rule-file How do I test a Codex rule file to check it works? https://latestn.com/tool/codex/permissions-and-security/set-token-expiration-limit How do I set an expiration limit for Codex access tokens? https://latestn.com/tool/codex/permissions-and-security/set-up-daybreak How do I set up Daybreak Defense Factory to scan a GitHub repository with Codex Security? https://latestn.com/tool/codex/permissions-and-security/shell-wrappers-compound-commands How does Codex handle shell wrappers and compound commands when matching rules? https://latestn.com/tool/ All entries in AI tools Change log: Time | Event | Change | Source 2026-11-20T13:42:00Z | changed | Recommended reasoning effort: — → xhigh | [1] 2026-11-20T13:42:00Z | changed | Recommended model: — → gpt-5.6-sol | [1] 2026-11-20T13:42:00Z | changed | Conversation command: — → $codex-security:deep-security-scan | [1] 2026-11-20T13:42:00Z | changed | Final action: — → Start scan | [1] 2026-11-20T13:42:00Z | changed | Deep scan toggle: — → Deep scan | [1] 2026-11-20T13:42:00Z | changed | Scan type option: — → Codebase | [1] 2026-11-20T13:42:00Z | changed | Navigation path: — → Security | [1] 2026-11-20T13:42:00Z | changed | recommended reasoning effort: xhigh → — | [1] 2026-11-20T13:42:00Z | changed | recommended model: gpt-5.6-sol → — | [1] 2026-11-20T13:42:00Z | changed | conversation command: $codex-security:deep-security-scan → — | [1] 2026-11-20T13:42:00Z | changed | final action: Start scan → — | [1] 2026-11-20T13:42:00Z | changed | scan type option: Deep scan → — | [1] 2026-11-20T13:42:00Z | changed | menu path: Security → — | [1] 2026-11-13T03:53:27Z | added | Entry created | — Changes for this entry as a feed: https://latestn.com/tool/codex/permissions-and-security/start-deep-security-scan/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/start-deep-security-scan POST: https://latestn.com/dispute/tool/codex/permissions-and-security/start-deep-security-scan with claim, evidence_url, and optionally field and contact (form-encoded or JSON) GET: https://latestn.com/dispute/tool/codex/permissions-and-security/start-deep-security-scan?claim={what is wrong}&evidence_url={link} How to cite: LatestN. (2026). How do I start a deep security scan in Codex? Revision 2, last verified 2026-11-20T13:42:00Z. https://latestn.com/tool/codex/permissions-and-security/start-deep-security-scan (accessed 2026-11-21T09:57:30Z). @misc{LatestN_tool_codex_permissions_and_security_start_deep_security_scan_r2, title = {How do I start a deep security scan in Codex?}, author = {{LatestN}}, year = {2026}, howpublished = {\url{https://latestn.com/tool/codex/permissions-and-security/start-deep-security-scan}}, note = {Revision 2; digest sha256:b8ef579270e5e213; last verified 2026-11-20T13:42:00Z; accessed 2026-11-21T09:57:30Z} } 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/start-deep-security-scan