Description
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.
Published: 2026-11-05
Score: 5.3 Medium
EPSS: n/a
KEV: No
Impact: Remote Code Execution
Action: Patch Now
AI Analysis

Impact

This vulnerability arises from improper neutralization of special elements in the Jinja2 template engine used by the FileBasedSkill.get_prompt function of DB‑GPT. The flaw allows an attacker to inject arbitrary template payloads that are evaluated by the engine, leading to server‑side template injection and potentially remote code execution. The weakness corresponds to CWE‑1336 (Template Injection) and CWE‑791 (Use of Uninitialized Variable).

Affected Systems

The flaw exists in eosphoros‑ai DB‑GPT versions up to and including 0.8.1. The affected component resides in packages/dbgpt-core/src/dbgpt/agent/skill/claude_skill/__init__.py. The patch that resolves the issue is available in release v0.8.2, and the corresponding commit identifier is a9e7a3c026d114fcfb4ffe3eaf78851a636ded16.

Risk and Exploitability

The CVSS score for this vulnerability is 5.3, indicating a moderate severity. The EPSS score is not available, and the vulnerability is not listed in the CISA KEV catalog. Attack sources are remote, and the exploit has been publicly disclosed. Organizations should treat this as a moderate but actionable risk; remote attackers could potentially gain code execution if the template engine processes unsanitized data. Updating to the patched version mitigates the risk, while other controls can reduce exploitation likelihood.

Generated by OpenCVE AI on November 5, 2026 at 14:39 UTC.

Remediation

No solution or workaround provided in the CVE record.

OpenCVE Recommended Actions

  • Apply the official patch by upgrading eosphoros‑ai DB‑GPT to version 0.8.2 or later, using the commit a9e7a3c026d114fcfb4ffe3eaf78851a636ded16.
  • If an upgrade cannot be performed immediately, ensure that any data fed to the FileBasedSkill.get_prompt function is thoroughly validated and sanitized to escape or discard Jinja2 special syntax, thereby preventing template injection.
  • Audit the source code or configuration to confirm that no unsanitized user input reaches the Jinja2 template engine, and restrict the scope of templated content to trusted internal sources.
  • Monitor logs for anomalous template rendering or unexpected command execution patterns indicative of an active exploitation attempt.

Generated by OpenCVE AI on November 5, 2026 at 14:39 UTC.

Tracking

Sign in to view the affected projects.

Advisories

No advisories yet.

History

Thu, 05 Nov 2026 13:00:00 +0000

Type Values Removed Values Added
Description 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.
Title eosphoros-ai DB-GPT Jinja2 Template __init__.py FileBasedSkill.get_prompt special elements in template engine
First Time appeared Eosphoros-ai
Eosphoros-ai db-gpt
Weaknesses CWE-1336
CWE-791
CPEs cpe:2.3:a:eosphoros-ai:db-gpt:*:*:*:*:*:*:*:*
Vendors & Products Eosphoros-ai
Eosphoros-ai db-gpt
References
Metrics cvssV2_0

{'score': 7.5, 'vector': 'AV:N/AC:L/Au:N/C:P/I:P/A:P/E:POC/RL:OF/RC:C'}

cvssV3_0

{'score': 6.3, 'vector': 'CVSS:3.0/AV:N/AC:L/PR:N/UI:R/S:U/C:L/I:L/A:L/E:P/RL:O/RC:C'}

cvssV3_1

{'score': 6.3, 'vector': 'CVSS:3.1/AV:N/AC:L/PR:N/UI:R/S:U/C:L/I:L/A:L/E:P/RL:O/RC:C'}

cvssV4_0

{'score': 5.3, 'vector': 'CVSS:4.0/AV:N/AC:L/AT:N/PR:N/UI:P/VC:L/VI:L/VA:L/SC:N/SI:N/SA:N/E:P'}

Subscriptions

Eosphoros-ai Db-gpt
cve-icon MITRE

Status: PUBLISHED

Assigner: VulDB

Published:

Updated: 2026-11-05T12:45:21.513Z

Reserved: 2026-11-05T06:17:58.263Z

Link: CVE-2026-123020

cve-icon Vulnrichment

No data.

cve-icon NVD

Status : Deferred

Published: 2026-11-05T13:17:07.280

Modified: 2026-11-05T13:17:07.433

Link: CVE-2026-123020

cve-icon Redhat

No data.

cve-icon OpenCVE Enrichment

Updated: 2026-11-05T14:45:15Z

Weaknesses
  • CWE-1336

    Improper Neutralization of Special Elements Used in a Template Engine

  • CWE-791

    Incomplete Filtering of Special Elements