Answer: For enforcement mode you can choose Block (the default) or Alert only. For On AIRS failure you can choose Allow prompts (the default) or Block prompts. Status: Confirmed Entry: tool/codex/permissions-and-security/prisma-airs-enforcement-modes Revision: 1 Digest: sha256:6e2067173e2ff003 (changes whenever the content changes) Timeline: Created: 2026-11-13T03:50:16Z Last changed: 2026-11-13T03:50:16Z Last verified: 2026-11-20T13:38:26Z Next check: 2026-11-21T13:38:26Z Check interval: Daily Expected change: No fixed schedule Data: Field | Value | Source | As of Enforcement mode option 1 | Block | [1] | 2026-11-20 Enforcement mode option 2 | Alert only | [1] | 2026-11-20 On AIRS failure option 1 | Allow prompts | [1] | 2026-11-20 On AIRS failure option 2 | Block prompts | [1] | 2026-11-20 Sources: [1] OpenAI. "Prisma AIRS". https://learn.chatgpt.com/docs/enterprise/prisma-airs.md Role: primary. Accessed: 2026-11-20T13:38:26Z Quote: "**Block**: Stop the prompt before it reaches the model. This is the default." (Supports: Enforcement mode option 1) Quote: "**Alert only**: Record the detection and allow the prompt to continue." (Supports: Enforcement mode option 2) Quote: "**Allow prompts**: Continue without a completed scan. This is the default." (Supports: On AIRS failure option 1) Quote: "**Block prompts**: Stop the prompt until Prisma AIRS can scan it." (Supports: On AIRS failure option 2) Snapshot SHA-256: 16f6c8a3fcc34cf70f5fd77e17b186517f27cc66be494f35850331c679a6a0b2 (captured 2026-11-13T03:50:14Z) 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 2026-11-13T03:50:16Z, so the values verified then were kept. Cross-check: not-available at 2026-11-20T13:38:26Z. No independent second source is configured for this entry Last successful check: 2026-11-20T13:38:26Z Last attempt: 2026-11-20T13:38:26Z Notes and limitations: Extracted automatically from a single official source (section "Choose how to handle prompts"). Related: https://latestn.com/tool/codex/permissions-and-security/read-only-triage-requirements What are the requirements to run read-only triage in Codex? 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/prepare-evidence-for-hardening What evidence should I provide to Codex Security when proposing security hardening? 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/ All entries in AI tools Change log: Time | Event | Change | Source 2026-11-13T03:50:16Z | added | Entry created | — Changes for this entry as a feed: https://latestn.com/tool/codex/permissions-and-security/prisma-airs-enforcement-modes/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/prisma-airs-enforcement-modes POST: https://latestn.com/dispute/tool/codex/permissions-and-security/prisma-airs-enforcement-modes with claim, evidence_url, and optionally field and contact (form-encoded or JSON) GET: https://latestn.com/dispute/tool/codex/permissions-and-security/prisma-airs-enforcement-modes?claim={what is wrong}&evidence_url={link} How to cite: LatestN. (2026). What enforcement modes and failure behaviors can I choose for Prisma AIRS in Codex? Revision 1, last verified 2026-11-20T13:38:26Z. https://latestn.com/tool/codex/permissions-and-security/prisma-airs-enforcement-modes (accessed 2026-11-21T10:03:41Z). @misc{LatestN_tool_codex_permissions_and_security_prisma_airs_enforcement_modes_r1, title = {What enforcement modes and failure behaviors can I choose for Prisma AIRS in Codex?}, author = {{LatestN}}, year = {2026}, howpublished = {\url{https://latestn.com/tool/codex/permissions-and-security/prisma-airs-enforcement-modes}}, note = {Revision 1; digest sha256:6e2067173e2ff003; last verified 2026-11-20T13:38:26Z; accessed 2026-11-21T10:03:41Z} } 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/prisma-airs-enforcement-modes