# CVE-2026-63377: TAKO AI Agent for Okta: Unauthenticated first-run administrator takeover

Status: published. Published: 2026-10-30. Updated: 2026-11-05.

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.

## Remediation

- fix: okta-ai-agent (pip): GitHub reports patched versions v3.0.1-beta. Check the advisory for the affected release branch. (source: GitHub GHSA-536w-42p8-3qv9) — https://github.com/fctr-id/okta-ai-agent/security/advisories/GHSA-536w-42p8-3qv9

## Affected products and versions

- fctr-id / okta-ai-agent: < 3.0.1-beta (affected). Source: CNA: GitHub_M
-  / okta-ai-agent (okta-ai-agent): v3.0.0-beta (affected, GitHub advisory range). Source: GitHub GHSA-536w-42p8-3qv9

## Severity and prioritization

- CVSS 3.1: 9.8 (critical); CVSS:3.1/AV:N/AC:L/PR:N/UI:N/S:U/C:H/I:H/A:H; source: CNA: GitHub_M

- CVSS 3.1: 9.8 (critical); CVSS:3.1/AV:N/AC:L/PR:N/UI:N/S:U/C:H/I:H/A:H; source: NVD: security-advisories@github.com

- CISA KEV: No listing in collected sources

- EPSS: 0.40% as of 2026-11-04; percentile 34.12%

- SSVC: exploitation poc; automatable yes; technical impact total; source ADP: CISA-ADP

- Weaknesses: CWE-306

## Exploit evidence

- exploit: https://github.com/fctr-id/okta-ai-agent/security/advisories/GHSA-536w-42p8-3qv9 (ADP: CISA-ADP)

## References

- https://github.com/fctr-id/okta-ai-agent/security/advisories/GHSA-536w-42p8-3qv9 (CNA: GitHub_M; x_refsource_CONFIRM)

- https://github.com/fctr-id/okta-ai-agent/commit/3b5ccaff8423cdfa6d26f5e133c01b8b71148df4 (CNA: GitHub_M; x_refsource_MISC)

- https://github.com/fctr-id/okta-ai-agent/releases/tag/v3.0.1-beta (CNA: GitHub_M; x_refsource_MISC)

- https://github.com/fctr-id/okta-ai-agent/security/advisories/GHSA-536w-42p8-3qv9 (ADP: CISA-ADP; exploit)

- https://github.com/fctr-id/okta-ai-agent/commit/3b5ccaff8423cdfa6d26f5e133c01b8b71148df4 (security-advisories@github.com)

- https://github.com/fctr-id/okta-ai-agent/releases/tag/v3.0.1-beta (security-advisories@github.com)

- https://github.com/fctr-id/okta-ai-agent/security/advisories/GHSA-536w-42p8-3qv9 (security-advisories@github.com)

- https://github.com/fctr-id/okta-ai-agent/security/advisories/GHSA-536w-42p8-3qv9 (GitHub Security Advisories; advisory)

## Provenance

- CNA: GitHub_M: https://www.cve.org/CVERecord?id=CVE-2026-63377; retrieved 2026-11-05; source updated 2026-11-05

- NVD: https://nvd.nist.gov/vuln/detail/CVE-2026-63377; retrieved 2026-11-03; source updated 2026-11-02

- GitHub Security Advisories: https://github.com/fctr-id/okta-ai-agent/security/advisories/GHSA-536w-42p8-3qv9; retrieved 2026-11-04; source updated 2026-07-16

- FIRST EPSS: https://api.first.org/data/v1/epss?cve=CVE-2026-63377; retrieved 2026-11-05; source updated Not reported

Revision: 6b1f6d0707eae1a8ecaab94952706d9cc58f1e8cd2ef15669ffd3978bda7824c

Canonical: https://y2.dev/cve/CVE-2026-63377

## Agent and API access

Public CVE pages, Markdown, and JSON are free to read without an account or API key.

- Public catalog: https://y2.dev/cve/index.json. Follow nextCursor with the same search, filters, sort, and limit (1–100). A null cursor marks the end.

- WebMCP: search_cve_disclosures, get_cve_disclosure, get_cve_page_markdown, get_y2_cve_access. Available in compatible browsers.

- Cyber API: https://api.y2.dev/api/v2/cyber/cves and https://api.y2.dev/api/v2/cyber/cves/{cveId}.

- Y2 Pro or Elite: create a workspace API key with the intel:cyber scope and send Authorization: Bearer <Y2_API_KEY>. Setup: https://y2.dev/docs/api/create-key.

- x402: Pay per request without an account or API key. Omit Authorization, read the HTTP 402 PAYMENT-REQUIRED challenge, validate its current requirements, and retry with PAYMENT-SIGNATURE through an authorized payment client. These browser tools never make payments. Guide: https://y2.dev/docs/api/x402.

- OpenAPI: https://y2.dev/api/openapi.yaml. Agent access metadata: https://y2.dev/cve/agent.json.

Collected public records only. Check source status for coverage and freshness.