Answer: To start a scan, open **Scans** and select **+ Scan**, then select a repository or folder, choose **Codebase** or **Changes**, set the scope, choose a model and reasoning effort, and select **Start scan**. Status: Confirmed Entry: tool/codex/permissions-and-security/start-security-scan Revision: 1 Digest: sha256:5594902d4de687c4 (changes whenever the content changes) Timeline: Created: 2026-11-13T03:53:45Z Last changed: 2026-11-13T03:53:45Z Last verified: 2026-11-20T13:42:17Z Next check: 2026-11-21T13:42:17Z Check interval: Daily Expected change: No fixed schedule Data: Field | Value | Source | As of first step | Open **Scans** and select **+ Scan**. | [1] | 2026-11-20 scan type options | **Codebase** | [1] | 2026-11-20 final step | Select **Start 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. "Use the Codex Security workbench". https://learn.chatgpt.com/docs/security/plugin/workbench.md Role: primary. Accessed: 2026-11-20T13:42:17Z Quote: "Open **Scans** and select **+ Scan**." (Supports: first step) Quote: "Choose **Codebase** to scan a repository or **Changes** to review a" (Supports: scan type options) Quote: "Select **Start scan**." (Supports: final step) Quote: "use `gpt-5.6-sol`" (Supports: recommended model) Quote: "with `xhigh` reasoning effort." (Supports: recommended reasoning effort) Snapshot SHA-256: 2f90053b15a0195a88a72a651cbfe574c5f52f750e7de88b740ed3cb496986f6 (captured 2026-11-13T03:53:45Z) 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 2026-11-13T03:53:45Z, so the values verified then were kept. Cross-check: not-available at 2026-11-20T13:42:17Z. No independent second source is configured for this entry Last successful check: 2026-11-20T13:42:17Z Last attempt: 2026-11-20T13:42:17Z Notes and limitations: Extracted automatically from a single official source (section "Start a scan"). Related: 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/threat-model-contents What does a Codex threat model include for a repository? https://latestn.com/tool/codex/permissions-and-security/track-findings-issue-advisory How do I get Codex to create a GitHub issue or draft security advisory for findings? 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/codex/permissions-and-security/start-deep-security-scan How do I start a deep security scan in Codex? 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/ All entries in AI tools Change log: Time | Event | Change | Source 2026-11-13T03:53:45Z | added | Entry created | — Changes for this entry as a feed: https://latestn.com/tool/codex/permissions-and-security/start-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-security-scan POST: https://latestn.com/dispute/tool/codex/permissions-and-security/start-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-security-scan?claim={what is wrong}&evidence_url={link} How to cite: LatestN. (2026). How do I start a security scan in the Codex Security workbench? Revision 1, last verified 2026-11-20T13:42:17Z. https://latestn.com/tool/codex/permissions-and-security/start-security-scan (accessed 2026-11-21T10:01:10Z). @misc{LatestN_tool_codex_permissions_and_security_start_security_scan_r1, title = {How do I start a security scan in the Codex Security workbench?}, author = {{LatestN}}, year = {2026}, howpublished = {\url{https://latestn.com/tool/codex/permissions-and-security/start-security-scan}}, note = {Revision 1; digest sha256:5594902d4de687c4; last verified 2026-11-20T13:42:17Z; accessed 2026-11-21T10:01:10Z} } 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-security-scan