# CVE-2026-77932: DB-GPT unauthenticated remote code execution

Source: https://junglewise.ai/threats/cve-2026-77932-db-gpt-through-0-8-2-contains-an-unauthenticated-remote-code  
Publisher: Junglewise Threat Intelligence, https://junglewise.ai/threats  
Published: 2026-10-20. Updated: 2026-10-20  
License: CC BY 4.0 with a link back

CVE-2026-77932 · Severity: critical · CVSS 9.8 · Published 2026-10-20

DB-GPT is an AI agent platform that provides database query and analytics capabilities. An unauthenticated attacker can exploit a mock authentication function to gain admin privileges and execute arbitrary Python or bash code as root on the server, potentially compromising the entire system and accessing the bundled database.

Technologies: [Eosphoros-Ai DB-GPT](https://junglewise.ai/threats/technologies/db-gpt). Vendors: [Eosphoros-Ai](https://junglewise.ai/threats/vendors/eosphoros-ai).

## Quick answers

**Is CVE-2026-77932 exploited in the wild?** No. Junglewise Threat Intelligence has no report of CVE-2026-77932 being exploited in the wild.

**How severe is CVE-2026-77932?** Critical severity, with a CVSS score of 9.8, published 20 October 2026.

**Which products and versions are affected?** Eosphoros-Ai DB-GPT through 0.8.2.

**Is there a fix for CVE-2026-77932?** No fixed version is recorded yet. Check the vendor's advisory in the references below. If you run it, Junglewise drafts a mitigation that fits your setup and applies it once you approve, with senior security engineers behind it.

**How is CVE-2026-77932 attacked?** It is attacked over the network, in a software library.

**Am I affected by CVE-2026-77932?** Check whether you run Eosphoros-Ai DB-GPT at an affected version. Junglewise does that check for you around the clock: connect your code, cloud and domains, and it matches new vulnerabilities like this one against what you actually run and tells you when one reaches you.

## Technical details

The /api/v1/chat/react-agent endpoint uses a mock get_user_from_headers function that grants admin role to all callers without authentication. Attackers can exploit the ReAct agent's unsandboxed code_interpreter and shell_interpreter tools to execute arbitrary Python or bash commands as root. This is a network-accessible, unauthenticated remote code execution vulnerability with no preconditions beyond network access.

## Affected products

- eosphoros-ai DB-GPT through 0.8.2

## Timeline

- 2026-10-20: disclosed

## References

- [https://pypi.org/](https://pypi.org/)
- [https://github.com/eosphoros-ai/DB-GPT/blob/83609c471266607490b24e72188311efa23a0d16/packages/dbgpt-app/src/dbgpt_app/openapi/api_v1/tools/code_interpreter.py](https://github.com/eosphoros-ai/DB-GPT/blob/83609c471266607490b24e72188311efa23a0d16/packages/dbgpt-app/src/dbgpt_app/openapi/api_v1/tools/code_interpreter.py)

## Related threats

- [eosphoros-ai DB-GPT remote code execution in HuggingFace adapter](https://junglewise.ai/threats/cve-2026-123019-a-weakness-has-been-identified-in-eosphoros-ai-db-gpt-up-to-0-8)
- [eosphoros-ai DB-GPT code injection in CodeAction](https://junglewise.ai/threats/cve-2026-123018-a-security-flaw-has-been-discovered-in-eosphoros-ai-db-gpt-up-to)
- [DB-GPT directory traversal in use_example_file](https://junglewise.ai/threats/cve-2026-51863-db-gpt-v0-7-5-and-0-8-0-contains-directory-traversal-in-use)
- [DB-GPT hardcoded credentials in default Docker configuration](https://junglewise.ai/threats/cve-2026-77933-db-gpt-through-0-8-2-contains-a-hardcoded-credentials)
- [DB-GPT sandbox API fallback to LocalRuntime code execution](https://junglewise.ai/threats/cve-2026-51869-db-gpt-v0-8-0-sandbox-api-silently-falls-back-to-localruntime-and)