Answer: To run read-only triage, you send a prompt using $codex-security:triage-finding against the repository, and for Jira or Linear issues you keep the source system read-only by instructing not to change the source issues. Codex then checks the current source and applicable SECURITY.md policy and returns a verdict for every input finding. Status: Confirmed Entry: tool/codex/permissions-and-security/read-only-triage-requirements Revision: 2 Digest: sha256:34d7fb81b9d0da05 (changes whenever the content changes) Timeline: Created: 2026-11-13T03:53:41Z Last changed: 2026-11-18T13:35:56Z (Output per finding: — → returns a verdict for every input finding) Last verified: 2026-11-20T13:42:14Z Next check: 2026-11-21T13:42:14Z Check interval: Daily Expected change: No fixed schedule Data: Field | Value | Source | As of Prompt command | $codex-security:triage-finding | [1] | 2026-11-20 Jira/Linear read-only instruction | Do not change the source issues. | [1] | 2026-11-20 Policy checked | SECURITY.md | [1] | 2026-11-20 Output per finding | returns a verdict for every input finding | [1] | 2026-11-20 Sources: [1] OpenAI. "Triage a backlog". https://learn.chatgpt.com/docs/security/plugin/triage-backlog.md Role: primary. Accessed: 2026-11-20T13:42:14Z Quote: "Use $codex-security:triage-finding to triage these existing security findings against this repository:" (Supports: Prompt command) Quote: "Do not change the source issues." (Supports: Jira/Linear read-only instruction) Quote: "Codex checks the current source and applicable `SECURITY.md` policy, then" (Supports: Policy checked) Quote: "returns a verdict for every input finding." (Supports: Output per finding) Snapshot SHA-256: 0c34ee357282fe56f59a21b390e25cd5c7ce2d50064a3cb60cd8fb86af5e4698 (captured 2026-11-17T14:07:30Z) 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 2026-11-17T14:07:31Z, so the values verified then were kept. Cross-check: not-available at 2026-11-20T13:42:14Z. No independent second source is configured for this entry Last successful check: 2026-11-20T13:42:14Z Last attempt: 2026-11-20T13:42:14Z Notes and limitations: Extracted automatically from a single official source (section "Run read-only triage"). Related: https://latestn.com/tool/codex/permissions-and-security/require-approval-for-sensitive-commands How do I require approval for sensitive commands in Codex? https://latestn.com/tool/codex/permissions-and-security/restrict-network-destinations How do I restrict network destinations for Codex Cloud and local Codex? https://latestn.com/tool/codex/permissions-and-security/review-findings-across-scans How do I review findings across scans in the Codex Security workbench? https://latestn.com/tool/codex/permissions-and-security/prepare-evidence-vulnerability-report What evidence should I provide to Codex before writing a vulnerability report? https://latestn.com/tool/codex/permissions-and-security/preset-domain-lists What preset domain lists are available for Codex Cloud (Legacy) internet access? https://latestn.com/tool/codex/permissions-and-security/prisma-airs-enforcement-modes What enforcement modes and failure behaviors can I choose for Prisma AIRS in Codex? https://latestn.com/tool/ All entries in AI tools Change log: Time | Event | Change | Source 2026-11-18T13:35:56Z | changed | Output per finding: — → returns a verdict for every input finding | [1] 2026-11-18T13:35:56Z | changed | Policy checked: — → SECURITY.md | [1] 2026-11-18T13:35:56Z | changed | Prompt command: — → $codex-security:triage-finding | [1] 2026-11-18T13:35:56Z | changed | output: returns a verdict for every input finding → — | [1] 2026-11-18T13:35:56Z | changed | policy checked: SECURITY.md → — | [1] 2026-11-18T13:35:56Z | changed | triage command: $codex-security:triage-finding → — | [1] 2026-11-13T03:53:41Z | added | Entry created | — Changes for this entry as a feed: https://latestn.com/tool/codex/permissions-and-security/read-only-triage-requirements/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/read-only-triage-requirements POST: https://latestn.com/dispute/tool/codex/permissions-and-security/read-only-triage-requirements with claim, evidence_url, and optionally field and contact (form-encoded or JSON) GET: https://latestn.com/dispute/tool/codex/permissions-and-security/read-only-triage-requirements?claim={what is wrong}&evidence_url={link} How to cite: LatestN. (2026). What are the requirements to run read-only triage in Codex? Revision 2, last verified 2026-11-20T13:42:14Z. https://latestn.com/tool/codex/permissions-and-security/read-only-triage-requirements (accessed 2026-11-21T10:06:50Z). @misc{LatestN_tool_codex_permissions_and_security_read_only_triage_requirements_r2, title = {What are the requirements to run read-only triage in Codex?}, author = {{LatestN}}, year = {2026}, howpublished = {\url{https://latestn.com/tool/codex/permissions-and-security/read-only-triage-requirements}}, note = {Revision 2; digest sha256:34d7fb81b9d0da05; last verified 2026-11-20T13:42:14Z; accessed 2026-11-21T10:06:50Z} } 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/read-only-triage-requirements