Answer in brief
CVE-2026-77932 records a Critical severity (CVSS 9.3) vulnerability in DB-GPT through 0.8.2 Unauthenticated RCE via /api/v1/chat/react-agent. The current sources do not mark it as known exploited. The current feed maps eosphoros-ai/DB-GPT (generic). Check affected ranges and fixed versions before updating.
Analysis pending evidence review
HOL Guard separates source facts from reviewed analysis. See the methodology.
CVSS is 9.3. The current sources do not mark it as known exploited. Treat this as a source-backed prioritization signal, not a statement about your environment.
Analysis status
Analysis pending evidence review
Factual feed record only; HOL analysis is not approved for indexing. Read the methodology.
The current feed maps eosphoros-ai/DB-GPT (generic). Check affected ranges and fixed versions before updating.
| Package | Affected range | Fixed version |
|---|---|---|
| eosphoros-ai/DB-GPTgeneric | >=0 <=0.8.2 | Not reported |
Published upstream
Oct 20, 2026
Evidence: source:cvelist:source_dates:source-dates:recordSource modified
Oct 20, 2026
Evidence: source:cvelist:source_dates:source-dates:recordFirst seen by HOL
Oct 20, 2026
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.
Quoted source text, attributed separately from HOL analysis.