# CVE-2026-63378: TAKO AI Agent for Okta: Authenticated Python execution through validator bypass

Status: published. Published: 2026-10-30. Updated: 2026-11-02.

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, any authenticated user with a valid `fctr_session` cookie can submit arbitrary Python source in the `script_code` field of `POST /api/react/execute-script`, without administrator privilege. In `src/api/routers/react_stream.py`, the source is stored with `skip_discovery=True`, bypassing AI-based content filtering, and is passed to `validate_generated_code` in `src/utils/security_config.py`. `BLOCKED_PATTERNS` recognizes direct `__import__` calls but misses the import name passed as a string, `getattr` is in `ALLOWED_BUILTINS`, and the AST checker handles `ast.Name` and `ast.Attribute` targets but fails to handle `ast.Call` targets. Dynamic `getattr` call chains through `__builtins__` therefore evade validation. The `_write_temp_script` helper writes the accepted code to disk, and `asyncio.create_subprocess_exec()` executes it as the application process user, which is root in the default container. Command output is returned as Server-Sent Events through `GET /api/react/stream-react-updates?process_id=<id>`. The resulting container compromise can disclose environment secrets including Okta API tokens and the JWT key, expose the SQLite database, and permit backend-service pivoting and persistence. This issue is fixed in version 3.0.1-beta.

## Remediation

No remediation reported in collected sources

## Affected products and versions

- fctr-id / okta-ai-agent: < 3.0.1-beta (affected). Source: CNA: GitHub_M

## Severity and prioritization

- CVSS 3.1: 8.8 (high); CVSS:3.1/AV:N/AC:L/PR:L/UI:N/S:U/C:H/I:H/A:H; source: CNA: GitHub_M

- CISA KEV: No listing in collected sources

- EPSS: 0.36% as of 2026-11-02; percentile 29.92%

- SSVC: exploitation none; automatable no; technical impact total; source ADP: CISA-ADP

- Weaknesses: CWE-94

## Exploit evidence

No exploit evidence in collected sources. This is not proof of no exploitation.

## References

- https://github.com/fctr-id/okta-ai-agent/security/advisories/GHSA-r9q7-6784-7rc6 (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)

## Provenance

- CNA: GitHub_M: https://www.cve.org/CVERecord?id=CVE-2026-63378; retrieved 2026-11-02; source updated 2026-11-02

- FIRST EPSS: https://api.first.org/data/v1/epss?cve=CVE-2026-63378; retrieved 2026-11-02; source updated Not reported

Revision: 241f1ff10841e986405e1edeb2e7b16854ab923761988ae773206ea95176ed54

Canonical: https://y2.dev/cve/CVE-2026-63378

## 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.