Answer: You review the Agent Security policy in the Admin Console under Agent security, which replaces Policies & Configuration. Status: Confirmed Entry: tool/chatgpt/permissions-and-security/review-agent-security-policy Revision: 1 Digest: sha256:16a515f784704975 (changes whenever the content changes) Timeline: Created: 2026-11-15T13:44:36Z Last changed: 2026-11-15T13:44:36Z Last verified: 2026-11-20T13:37:32Z Next check: 2026-11-21T13:37:32Z Check interval: Daily Expected change: No fixed schedule Data: Field | Value | Source | As of Location | Admin Console → Agent security | [1] | 2026-11-20 Policy settings | Global baseline and any Local overrides | [1] | 2026-11-20 Feature access location | Admin Console → Permissions | [1] | 2026-11-20 Sources: [1] OpenAI. "Local computer access for Work Cloud and dots". https://learn.chatgpt.com/docs/enterprise/cloud-local-access.md Role: primary. Accessed: 2026-11-20T13:37:32Z Quote: "Open Admin Console → Agent security. It replaces Policies & Configuration." (Supports: Location) Quote: "Review the Global baseline and any Local overrides." (Supports: Policy settings) Quote: "Use Admin Console → Permissions." (Supports: Feature access location) Snapshot SHA-256: 79be3c58a66ad22607caa6c45890cda91375f220cba85556e6b1ae14b932bad6 (captured 2026-11-17T14:01:25Z) 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 2026-11-17T14:01:25Z, so the values verified then were kept. Cross-check: not-available at 2026-11-20T13:37:32Z. No independent second source is configured for this entry Last successful check: 2026-11-20T13:37:32Z Last attempt: 2026-11-20T13:37:32Z Notes and limitations: Extracted automatically from a single official source (section "Review your policy in Agent Security"). Related: https://latestn.com/tool/chatgpt/permissions-and-security/review-approve-outlook-permissions How do I review and approve the Microsoft permissions ChatGPT requests for the Outlook Email app? https://latestn.com/tool/chatgpt/permissions-and-security/review-approve-permissions How do I review and approve Microsoft permissions for the SharePoint app in ChatGPT? https://latestn.com/tool/chatgpt/permissions-and-security/revoke-icloud-app-password How do I review or revoke an iCloud app-specific password used in ChatGPT? https://latestn.com/tool/chatgpt/permissions-and-security/restrict-app-connections-verified-domain How do I restrict app connections using a verified domain for OpenAI identity? https://latestn.com/tool/chatgpt/permissions-and-security/restrict-gpt-action-domains How do I restrict which external domains ChatGPT GPT actions can access? https://latestn.com/tool/chatgpt/permissions-and-security/restrict-or-expire-shared-link Can I restrict a shared ChatGPT link to specific people or set an expiration date? https://latestn.com/tool/ All entries in AI tools Change log: Time | Event | Change | Source 2026-11-15T13:44:36Z | added | Entry created | — Changes for this entry as a feed: https://latestn.com/tool/chatgpt/permissions-and-security/review-agent-security-policy/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/chatgpt/permissions-and-security/review-agent-security-policy POST: https://latestn.com/dispute/tool/chatgpt/permissions-and-security/review-agent-security-policy with claim, evidence_url, and optionally field and contact (form-encoded or JSON) GET: https://latestn.com/dispute/tool/chatgpt/permissions-and-security/review-agent-security-policy?claim={what is wrong}&evidence_url={link} How to cite: LatestN. (2026). Where do I review the Agent Security policy for local computer access in ChatGPT? Revision 1, last verified 2026-11-20T13:37:32Z. https://latestn.com/tool/chatgpt/permissions-and-security/review-agent-security-policy (accessed 2026-11-21T10:04:32Z). @misc{LatestN_tool_chatgpt_permissions_and_security_review_agent_security_policy_r1, title = {Where do I review the Agent Security policy for local computer access in ChatGPT?}, author = {{LatestN}}, year = {2026}, howpublished = {\url{https://latestn.com/tool/chatgpt/permissions-and-security/review-agent-security-policy}}, note = {Revision 1; digest sha256:16a515f784704975; last verified 2026-11-20T13:37:32Z; accessed 2026-11-21T10:04:32Z} } 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/chatgpt/permissions-and-security/review-agent-security-policy