# CVE-2026-123018: eosphoros-ai DB-GPT CodeAction code_utils.py execute_code code injection

Status: published. Published: 2026-11-05. Updated: 2026-11-05.

A security flaw has been discovered in eosphoros-ai DB-GPT up to 0.8.2. This issue affects the function execute_code of the file code_utils.py of the component CodeAction. Performing a manipulation results in code injection. The attack can be initiated remotely. The exploit has been released to the public and may be used for attacks. The project was informed of the problem early through an issue report but has not responded yet.

## Remediation

No remediation reported in collected sources

## Affected products and versions

- eosphoros-ai / DB-GPT: 0.8.0 (affected); 0.8.1 (affected); 0.8.2 (affected). Source: CNA: VulDB

## Severity and prioritization

- CVSS 4.0: 6.9 (medium); CVSS:4.0/AV:N/AC:L/AT:N/PR:N/UI:N/VC:L/VI:L/VA:L/SC:L/SI:L/SA:L/E:P; source: CNA: VulDB

- CVSS 3.1: 8.3 (high); CVSS:3.1/AV:N/AC:L/PR:N/UI:N/S:C/C:L/I:L/A:L/E:P/RL:X/RC:C; source: CNA: VulDB

- CVSS 3.0: 8.3 (high); CVSS:3.0/AV:N/AC:L/PR:N/UI:N/S:C/C:L/I:L/A:L/E:P/RL:X/RC:C; source: CNA: VulDB

- CVSS 2.0: 7.5 (high); AV:N/AC:L/Au:N/C:P/I:P/A:P/E:POC/RL:ND/RC:C; source: CNA: VulDB

- CISA KEV: No listing in collected sources

- EPSS: Not available

- SSVC: Not available

- Weaknesses: CWE-94, CWE-74

## Exploit evidence

- exploit: https://github.com/ybyu-ieu/agent-security-advisories/blob/main/dbgpt/dbgpt-codeaction-native-subprocess-llm-code-execution.md (CNA: VulDB)

## References

- https://vuldb.com/vuln/431392 (CNA: VulDB; vdb-entry, technical-description)

- https://vuldb.com/vuln/431392/cti (CNA: VulDB; signature, permissions-required)

- https://vuldb.com/cve/CVE-2026-123018 (CNA: VulDB; third-party-advisory)

- https://vuldb.com/submit/1033094 (CNA: VulDB; third-party-advisory)

- https://github.com/eosphoros-ai/DB-GPT/issues/3287 (CNA: VulDB; issue-tracking)

- https://github.com/ybyu-ieu/agent-security-advisories/blob/main/dbgpt/dbgpt-codeaction-native-subprocess-llm-code-execution.md (CNA: VulDB; exploit)

- https://github.com/eosphoros-ai/DB-GPT/ (CNA: VulDB; product)

## Provenance

- CNA: VulDB: https://www.cve.org/CVERecord?id=CVE-2026-123018; retrieved 2026-11-05; source updated 2026-11-05

Revision: 5f184f2a361c844b332c3acb8906832276cab2c882f4631ba31bc1bc4b2dda19

Canonical: https://y2.dev/cve/CVE-2026-123018

## Agent and API access

Public CVE pages, Markdown, and JSON are free to read without an account or API key.

- Public catalog: https://y2.dev/cve/index.json. Follow nextCursor with the same search, filters, sort, and limit (1–100). A null cursor marks the end.

- WebMCP: search_cve_disclosures, get_cve_disclosure, get_cve_page_markdown, get_y2_cve_access. Available in compatible browsers.

- Cyber API: https://api.y2.dev/api/v2/cyber/cves and https://api.y2.dev/api/v2/cyber/cves/{cveId}.

- Y2 Pro or Elite: create a workspace API key with the intel:cyber scope and send Authorization: Bearer <Y2_API_KEY>. Setup: https://y2.dev/docs/api/create-key.

- x402: Pay per request without an account or API key. Omit Authorization, read the HTTP 402 PAYMENT-REQUIRED challenge, validate its current requirements, and retry with PAYMENT-SIGNATURE through an authorized payment client. These browser tools never make payments. Guide: https://y2.dev/docs/api/x402.

- OpenAPI: https://y2.dev/api/openapi.yaml. Agent access metadata: https://y2.dev/cve/agent.json.

Collected public records only. Check source status for coverage and freshness.