Answer: You can change the minimum severity independently for automatic and manual reviews, and add path-based overrides. By default, automatic reviews report High and Critical findings, while manually requested reviews report Medium, High, and Critical findings. Status: Confirmed Entry: tool/codex/settings/set-reporting-thresholds Revision: 2 Digest: sha256:42acf017da82ee58 (changes whenever the content changes) Timeline: Created: 2026-11-13T03:53:56Z Last changed: 2026-11-18T13:36:11Z (customization: — → change the minimum severity independently for automatic and manual reviews) Last verified: 2026-11-20T13:42:28Z Next check: 2026-11-21T13:42:28Z Check interval: Daily Expected change: No fixed schedule Data: Field | Value | Source | As of automatic review default thresholds | High | [1] | 2026-11-20 manual review default thresholds | Medium | [1] | 2026-11-20 customization | change the minimum severity independently for automatic and manual reviews | [1] | 2026-11-20 Sources: [1] OpenAI. "Security Review". https://learn.chatgpt.com/docs/security/security-review.md Role: primary. Accessed: 2026-11-20T13:42:28Z Quote: "automatic Codex Security Reviews report **High** and **Critical**" (Supports: automatic review default thresholds) Quote: "manually requested reviews report **Medium**, **High**, and **Critical** findings" (Supports: manual review default thresholds) Quote: "You can change the minimum severity independently for automatic and manual reviews, and add path-based overrides." (Supports: customization) Snapshot SHA-256: 5bb2ab6b4e9670b4f0436465f5d056dd21737eae976117f0c567a57ecab0c231 (captured 2026-11-17T14:07:47Z) 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 2026-11-17T14:07:51Z, so the values verified then were kept. Cross-check: not-available at 2026-11-20T13:42:28Z. No independent second source is configured for this entry Last successful check: 2026-11-20T13:42:28Z Last attempt: 2026-11-20T13:42:28Z Notes and limitations: Extracted automatically from a single official source (section "Set reporting thresholds"). Related: https://latestn.com/tool/codex/settings/set-service-tier-per-turn How do I set the service tier for a single turn in the Codex SDK? https://latestn.com/tool/codex/troubleshooting/codex-diagnostics-env-vars What environment variables can I use to diagnose Codex issues? https://latestn.com/tool/codex/troubleshooting/deep-scan-interruption-failure What should I do if a Codex deep scan is interrupted or fails? https://latestn.com/tool/codex/settings/pause-commit-monitoring Can I pause commit monitoring in Daybreak Defense Factory? https://latestn.com/tool/codex/settings/project-doc-fallback-filenames How do I customize the fallback filenames Codex looks for instead of AGENTS.md? https://latestn.com/tool/codex/settings/requirements-toml-location Where is the requirements.toml file located for Codex on Linux, macOS, and Windows? https://latestn.com/tool/ All entries in AI tools Change log: Time | Event | Change | Source 2026-11-18T13:36:11Z | changed | customization: — → change the minimum severity independently for automatic and manual reviews | [1] 2026-11-18T13:36:11Z | changed | manual review default thresholds: — → Medium | [1] 2026-11-18T13:36:11Z | changed | automatic review default thresholds: — → High | [1] 2026-11-18T13:36:11Z | changed | Customization method: change the minimum severity independently for automatic and manual reviews, and add path-based overrides → — | [1] 2026-11-18T13:36:11Z | changed | Default manual review threshold: Medium → — | [1] 2026-11-18T13:36:11Z | changed | Default automatic review threshold: High → — | [1] 2026-11-13T03:53:56Z | added | Entry created | — Changes for this entry as a feed: https://latestn.com/tool/codex/settings/set-reporting-thresholds/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/settings/set-reporting-thresholds POST: https://latestn.com/dispute/tool/codex/settings/set-reporting-thresholds with claim, evidence_url, and optionally field and contact (form-encoded or JSON) GET: https://latestn.com/dispute/tool/codex/settings/set-reporting-thresholds?claim={what is wrong}&evidence_url={link} How to cite: LatestN. (2026). How do I set reporting thresholds for Codex Security Review? Revision 2, last verified 2026-11-20T13:42:28Z. https://latestn.com/tool/codex/settings/set-reporting-thresholds (accessed 2026-11-21T09:53:06Z). @misc{LatestN_tool_codex_settings_set_reporting_thresholds_r2, title = {How do I set reporting thresholds for Codex Security Review?}, author = {{LatestN}}, year = {2026}, howpublished = {\url{https://latestn.com/tool/codex/settings/set-reporting-thresholds}}, note = {Revision 2; digest sha256:42acf017da82ee58; last verified 2026-11-20T13:42:28Z; accessed 2026-11-21T09:53:06Z} } 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/settings/set-reporting-thresholds