DB-GPT through 0.8.2 contains an unauthenticated remote code execution vulnerability because the /api/v1/chat/react-agent endpoint relies on a mock get_user_from_headers function that grants every caller the admin role. Unauthenticated attackers can send prompts that make the ReAct agent's unsandboxed code_interpreter and shell_interpreter tools run arbitrary Python or bash as root in the webserver container, including reaching the bundled database with default credentials.
Fix
Nothing published yet: no patch, vendor advisory or mitigation reference on NVD, no vendor advisory in the News for this CVE, not in CISA's KEV, no fixed package version. BaselineWatch does not guess at one.
Change history 1
- First seenCVSS 9.3NVD modified 2026-10-20 01:17
Affected (CPE criteria) 0
NVD has not attached CPE configurations yet.
References 4
- https://github.com/eosphoros-ai/DB-GPT/blob/83609c471266607490b24e72188311efa23a0d16/packages/dbgpt-app/src/dbgpt_app/openapi/api_v1/tools/code_interpreter.py#L39
- https://github.com/eosphoros-ai/DB-GPT/blob/83609c471266607490b24e72188311efa23a0d16/packages/dbgpt-serve/src/dbgpt_serve/utils/auth.py#L25
- https://www.lasso.security/vulnerability-database/cve-2026-77932
- https://www.vulncheck.com/advisories/db-gpt-through-0.8.2-unauthenticated-rce-via-api-v1-chat-react-agent