CVE-2026-51866

Deferred Deferred - Pending Action

Remote Code Execution in DB-GPT via Skill Upload

Publication date: 2026-09-30

Last updated on: 2026-10-01

Assigner: MITRE

Description

In DB-GPT 0.7.5 and 0.8.0, a skill uploaded through the real /api/v1/skills/upload route can later be executed through the real /api/v1/chat/react-agent flow.

CVSS Scores

EPSS Scores

Probability:
Percentile:

Meta Information

Published

2026-09-30

Last Modified

2026-10-01

Generated

2026-10-19

AI Q&A

2026-10-01

EPSS Evaluated

2026-10-18

NVD

CVE-2026-51866

Affected Vendors & Products

Vendor	Product	Version / Range
eosphoros-ai	db-gpt	0.7.5
eosphoros-ai	db-gpt	0.8.0

Helpful Resources

Exploitability

CWE

KEV

CWE ID	Description
CWE-94	The product constructs all or part of a code segment using externally-influenced input from an upstream component, but it does not neutralize or incorrectly neutralizes special elements that could modify the syntax or behavior of the intended code segment.

Attack-Flow Graph

Executive Summary

This vulnerability in DB-GPT versions 0.7.5 and 0.8.0 allows an attacker to upload a malicious skill via the /api/v1/skills/upload endpoint and later execute it through the /api/v1/chat/react-agent flow. This bypasses intended access controls and enables unauthorized code execution.

Detection Guidance

To detect this vulnerability, monitor for unauthorized skill uploads or executions in DB-GPT. Check logs for POST requests to /api/v1/skills/upload and subsequent GET/POST requests to /api/v1/chat/react-agent. Look for unexpected skill activations or unusual chat interactions.

Impact Analysis

An attacker could exploit this to run arbitrary code on your DB-GPT instance, potentially stealing data, installing malware, or disrupting services. This could lead to unauthorized access to sensitive information or system compromise.

Compliance Impact

This vulnerability could lead to unauthorized data access or exfiltration, violating GDPR's data protection requirements and HIPAA's safeguards for protected health information. Non-compliance may result in legal penalties and reputational damage.

Mitigation Strategies

Immediately upgrade DB-GPT to a version that patches this vulnerability. If upgrading is not possible, restrict access to the /api/v1/skills/upload and /api/v1/chat/react-agent endpoints to trusted users only.

Hi! I’m here to help you understand CVE-2026-51866. Ask me anything about the vulnerability, its impact, or mitigation strategies.

0/70