Answer: Send a prompt like "Use $codex-security:propose-security-hardening to analyze [scan directory or finding paths] against [source tree and revision]." The prompt should ask for evidence-backed structural hardening options with engineering tradeoffs, before-and-after diagrams, a migration plan, and an implementation handoff, without modifying the repository. Status: Confirmed Entry: tool/codex/permissions-and-security/run-propose-security-hardening-workflow Revision: 2 Digest: sha256:1859e1d45e12e995 (changes whenever the content changes) Timeline: Created: 2026-11-13T03:53:39Z Last changed: 2026-11-18T13:35:52Z (constraint: — → Do not modify the repository.) Last verified: 2026-11-20T13:42:10Z Next check: 2026-11-21T13:42:10Z Check interval: Daily Expected change: No fixed schedule Data: Field | Value | Source | As of workflow command | $codex-security:propose-security-hardening | [1] | 2026-11-20 prompt instruction | Send a prompt like: | [1] | 2026-11-20 constraint | Do not modify the repository. | [1] | 2026-11-20 Sources: [1] OpenAI. "Propose security hardening". https://learn.chatgpt.com/docs/security/plugin/security-hardening.md Role: primary. Accessed: 2026-11-20T13:42:10Z Quote: "Use $codex-security:propose-security-hardening to analyze [scan directory or finding paths] against [source tree and revision]." (Supports: workflow command) Quote: "Send a prompt like:" (Supports: prompt instruction) Quote: "Do not modify the repository." (Supports: constraint) Snapshot SHA-256: 2a805e0f0af6057db6477a0251b6b3d35a60cfa02128f7aa5383ce0cf5bae89d (captured 2026-11-17T14:07:27Z) 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 2026-11-17T14:07:25Z, so the values verified then were kept. Cross-check: not-available at 2026-11-20T13:42:10Z. No independent second source is configured for this entry Last successful check: 2026-11-20T13:42:10Z Last attempt: 2026-11-20T13:42:10Z Notes and limitations: Extracted automatically from a single official source (section "Run the workflow"). Related: https://latestn.com/tool/codex/permissions-and-security/run-security-scan-repository-folder How do I run a Codex Security scan on a repository or folder? https://latestn.com/tool/codex/permissions-and-security/sandbox-presets What sandbox presets are available in the Codex SDK Python library? https://latestn.com/tool/codex/permissions-and-security/sandbox-restrictions What does the Codex sandbox restrict the agent from doing on my machine? https://latestn.com/tool/codex/permissions-and-security/rule-fields What fields can I set in a Codex rule, such as pattern and decision? https://latestn.com/tool/codex/permissions-and-security/run-bulk-security-scans How do I run bulk security scans across multiple repositories with Codex Security? https://latestn.com/tool/codex/permissions-and-security/run-first-local-scan How do I run my first local security scan with the Codex Security plugin? https://latestn.com/tool/ All entries in AI tools Change log: Time | Event | Change | Source 2026-11-18T13:35:52Z | changed | constraint: — → Do not modify the repository. | [1] 2026-11-18T13:35:52Z | changed | repository constraint: Do not modify the repository. → — | [1] 2026-11-18T13:35:52Z | changed | outputs: evidence-backed structural hardening options with engineering tradeoffs, before-and-after diagrams, a migration plan, and an implementation handoff → — | [1] 2026-11-13T03:53:39Z | added | Entry created | — Changes for this entry as a feed: https://latestn.com/tool/codex/permissions-and-security/run-propose-security-hardening-workflow/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/run-propose-security-hardening-workflow POST: https://latestn.com/dispute/tool/codex/permissions-and-security/run-propose-security-hardening-workflow with claim, evidence_url, and optionally field and contact (form-encoded or JSON) GET: https://latestn.com/dispute/tool/codex/permissions-and-security/run-propose-security-hardening-workflow?claim={what is wrong}&evidence_url={link} How to cite: LatestN. (2026). How do I run the Codex Security propose-security-hardening workflow? Revision 2, last verified 2026-11-20T13:42:10Z. https://latestn.com/tool/codex/permissions-and-security/run-propose-security-hardening-workflow (accessed 2026-11-21T10:03:35Z). @misc{LatestN_tool_codex_permissions_and_security_run_propose_security_hardening_workflow_r2, title = {How do I run the Codex Security propose-security-hardening workflow?}, author = {{LatestN}}, year = {2026}, howpublished = {\url{https://latestn.com/tool/codex/permissions-and-security/run-propose-security-hardening-workflow}}, note = {Revision 2; digest sha256:1859e1d45e12e995; last verified 2026-11-20T13:42:10Z; accessed 2026-11-21T10:03:35Z} } 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/run-propose-security-hardening-workflow