CVE-2026-77932: Missing Authentication for Critical Function in eosphoros-ai DB-GPT
Description
DB-GPT versions up to 0.8.2 have a critical vulnerability allowing unauthenticated remote code execution via the /api/v1/chat/react-agent endpoint. This endpoint uses a mock authentication function that grants admin privileges to all callers, enabling attackers to execute arbitrary Python or bash commands as root within the webserver container and access the bundled database with default credentials.
CVSS v4.0
Score 9.3critical
Affected software
eosphoros-ai
DB-GPT
Run on your own infrastructure? Check whether these packages are installed with threat-finder — our free open-source scanner.
AI-Powered Analysis
Machine-generated threat intelligence
Technical Analysis
CVE-2026-77932 describes a missing authentication vulnerability in eosphoros-ai's DB-GPT up to version 0.8.2. The /api/v1/chat/react-agent endpoint relies on a mock get_user_from_headers function that incorrectly assigns admin role to any caller without authentication. This flaw allows unauthenticated attackers to send crafted prompts that cause the ReAct agent's unsandboxed code_interpreter and shell_interpreter tools to execute arbitrary code with root privileges on the webserver container, including access to the bundled database using default credentials.
Potential Impact
An unauthenticated remote attacker can achieve full remote code execution as root on the affected system hosting DB-GPT, potentially compromising the entire server and the bundled database. This represents a critical security risk with high impact on confidentiality, integrity, and availability.
Mitigation Recommendations
Patch status is not yet confirmed — check the vendor advisory for current remediation guidance. Until an official fix is available, restrict access to the vulnerable endpoint and avoid deploying affected versions in untrusted environments.
Technical Details
- Data Version
- 5.2
- Assigner Short Name
- VulnCheck
- Date Reserved
- 2026-08-21T17:52:36.079Z
- Cvss Version
- 4.0
- State
- PUBLISHED
Threat ID: 6ad6c1972cdf04f656e49571
Added to database: 10/20/2026, 01:19:19 UTC
Last enriched: 10/20/2026, 01:33:30 UTC
Last updated: 10/20/2026, 01:34:17 UTC
Views: 6
Community Reviews
0 reviewsCrowdsource mitigation strategies, share intel context, and vote on the most helpful responses. Sign in to add your voice and help keep defenders ahead.
Want to contribute mitigation steps or threat intel context? Sign in or create an account to join the community discussion.
Actions
Updates to AI analysis require Pro Console access. Upgrade inside Console → Billing.
Need more coverage?
Upgrade to Pro Console for AI refresh and higher limits.
For incident response and remediation, OffSeq services can help resolve threats faster.
Latest Threats
Check if your credentials are on the dark web
Instant breach scanning across billions of leaked records. Free tier available.