Template injection in eosphoros-ai DB-GPT skill prompt rendering
Key facts
- Attack vector
- Network
- Privileges required
- None
- User interaction
- Passive
- Attack complexity
- Low
- Attack requirements
- None
- Impact type
- Code execution
- Confidentiality · integrity · availability
- Low · Low · Low
- Fix status
- Fixed
Attack profile from CVSS 4.0 · CNA. Fix status from CNA. Impact type from CWE-1336.
Summary
eosphoros-ai DB-GPT versions 0.8.0 and 0.8.1 are affected. The FileBasedSkill.get_prompt function does not neutralize special elements in Jinja2 template input (CWE-1336). A remote attacker without privileges can exploit this if a user interacts with the application. A public exploit has been disclosed and is linked in the references.
Written with Claude Haiku 5.5 from the sources below · 2026-11-06
Description from the CNA
A security vulnerability has been detected in eosphoros-ai DB-GPT up to 0.8.1. The affected element is the function FileBasedSkill.get_prompt of the file packages/dbgpt-core/src/dbgpt/agent/skill/claude_skill/__init__.py of the component Jinja2 Template Handler. The manipulation leads to improper neutralization of special elements used in a template engine. The attack may be initiated remotely. The exploit has been disclosed publicly and may be used. Upgrading to version 0.8.2 is sufficient to fix this issue. The identifier of the patch is a9e7a3c026d114fcfb4ffe3eaf78851a636ded16. It is suggested to upgrade the affected component.
Why it matters now
SSVC decision points
CISA ADP · SSVC 2.0.3
- Exploitation
- Poc
- Automatable
- No
- Technical impact
- Partial
The decision (Track, Attend, Act) also depends on your mission and well-being impact; see CISA's SSVC guide.
Affected products
| Vendor | Product | Affected versions | Fixed in | Status | Source |
|---|---|---|---|---|---|
| eosphoros-ai | DB-GPT | 0.8.0; 0.8.1 | 0.8.2 | Patch available | CNA |
- DB-GPT Vendoreosphoros-ai Affected 0.8.0; 0.8.1 Fixed in 0.8.2 Patch available CNA
CPE names CNA · 1
| CPE | Versions | Role | Vendor |
|---|---|---|---|
| cpe:2.3:a:eosphoros-ai:db-gpt:*:*:*:*:*:*:*:* | — | — | — |
- cpe:2.3:a:eosphoros-ai:db-gpt:*:*:*:*:*:*:*:* Versions — — ·—
Remediation
Upgrade DB-GPT to version 0.8.2, which fixes the issue in patch a9e7a3c026d114fcfb4ffe3eaf78851a636ded16.
Written with Claude Haiku 5.5 from the sources below · 2026-11-06
- Fix · CNA DB-GPT (eosphoros-ai) Fixed in 0.8.2
Vendor assessments
Timeline
- 2026-11-05 Threatist record created from CVE-2026-123020
- 2026-11-05 Alias added: GHSA-x327-5gx8-j9v4
- 2026-11-05 CISA SSVC decision points changed
- 2026-11-05 Priority changed: LOW → MEDIUM
- 2026-11-06 Affected versions changed · Red Hat
- 2026-11-06 CVSS score added · Red Hat
References
Patch 3
More eosphoros-ai vulnerabilities
- TI-2026-76663 Hardcoded MySQL root credentials in DB-GPT docker-compose deployment CVSS 4.0CRITICAL 9.3
- TI-2026-76662 Unauthenticated remote code execution in DB-GPT via agent endpoint CVSS 4.0CRITICAL 9.3
- TI-2026-51243 DB-GPT v0.8.1 Path Traversal Arbitrary File Write via user_id Header CVSS 4.0CRITICAL 9.3
- TI-2024-10106 Arbitrary File Upload with Path Traversal in eosphoros-ai/db-gpt CVSS 3.1CRITICAL 9.8
- TI-2024-10105 Arbitrary File Write via DuckDB SQL Injection in eosphoros-ai/db-gpt CVSS 3.1CRITICAL 9.8
- TI-2024-10044 Arbitrary File Write via SQL Injection in eosphoros-ai/db-gpt CVSS 3.1CRITICAL 9.8
Sources
- CVE-2026-123020 · CVE Program
- CVE-2026-123020 · NVD
- FIRST EPSS
- GHSA-x327-5gx8-j9v4 · GitHub Advisory Database · CC BY 4.0
- CVE-2026-123020 · Red Hat security data · CC BY 4.0
This product uses the NVD API but is not endorsed or certified by the NVD. Sources and licences