Description
A security vulnerability has been detected in esengine DeepSeek-Reasonix up to 2.52.0. Affected is the function discoverDocs of the file internal/memory/doc.go. The manipulation leads to improper neutralization of input used for llm prompting. The attack can be initiated remotely. The exploit has been disclosed publicly and may be used. Upgrading to version 2.53.0 is able to address this issue. The identifier of the patch is 4ca33493a673c2788aa8598fbca2b2f47a69e1b8. It is suggested to upgrade the affected component.
Published: 2026-11-06
Score: 5.3 Medium
EPSS: n/a
KEV: No
Impact: Potential remote code execution via LLM prompting injection
Action: Patch
AI Analysis

Impact

A flaw in the internal/memory/doc.go discoverDocs function allows input that is not properly neutralized to be sent to the language model prompting engine. If an attacker supplies specially crafted data, the LLM may generate code or instructions that can be executed by the host, or otherwise manipulate the behavior of the system. The vulnerability could lead to unauthorized data exposure, tampering, or execution of malicious commands; it also undermines the integrity of generated responses.

Affected Systems

esengine DeepSeek‑Reasonix up to and including version 2.52.0 is impacted. The fix is available in release 2.53.0, identified by commit 4ca33493a673c2788aa8598fbca2b2f47a69e1b8.

Risk and Exploitability

The CVSS score of 5.3 indicates moderate severity. The EPSS score is not available, and the vulnerability is not listed in the CISA KEV catalog. Attackers can trigger the flaw remotely, as the component exposes a network interface that accepts prompting input. Publicly disclosed evidence shows that exploits can be constructed, so timely patching is recommended.

Generated by OpenCVE AI on November 6, 2026 at 15:01 UTC.

Remediation

No solution or workaround provided in the CVE record.

OpenCVE Recommended Actions

  • Upgrade to esengine DeepSeek‑Reasonix v2.53.0 or later, which contains a patched discoverDocs implementation.
  • Replace or modify the discoverDocs implementation to enforce explicit input sanitization before forwarding to the LLM, blocking unsupported characters or patterns that could trigger code generation.
  • If the application currently executes LLM output directly, disable that pipeline until a thorough audit is performed and introduce an approval step or audit trail for any commands generated by the LLM.

Generated by OpenCVE AI on November 6, 2026 at 15:01 UTC.

Tracking

Sign in to view the affected projects.

Advisories

No advisories yet.

History

Fri, 06 Nov 2026 13:45:00 +0000

Type Values Removed Values Added
Description A security vulnerability has been detected in esengine DeepSeek-Reasonix up to 2.52.0. Affected is the function discoverDocs of the file internal/memory/doc.go. The manipulation leads to improper neutralization of input used for llm prompting. The attack can be initiated remotely. The exploit has been disclosed publicly and may be used. Upgrading to version 2.53.0 is able to address this issue. The identifier of the patch is 4ca33493a673c2788aa8598fbca2b2f47a69e1b8. It is suggested to upgrade the affected component.
Title esengine DeepSeek-Reasonix doc.go discoverDocs llm prompting input
First Time appeared Esengine
Esengine deepseek-reasonix
Weaknesses CWE-1427
CWE-349
CPEs cpe:2.3:a:esengine:deepseek-reasonix:*:*:*:*:*:*:*:*
Vendors & Products Esengine
Esengine deepseek-reasonix
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

Esengine Deepseek-reasonix
cve-icon MITRE

Status: PUBLISHED

Assigner: VulDB

Published:

Updated: 2026-11-06T13:30:24.822Z

Reserved: 2026-11-06T08:28:48.613Z

Link: CVE-2026-123653

cve-icon Vulnrichment

No data.

cve-icon NVD

Status : Deferred

Published: 2026-11-06T14:17:10.923

Modified: 2026-11-06T14:17:11.107

Link: CVE-2026-123653

cve-icon Redhat

No data.

cve-icon OpenCVE Enrichment

Updated: 2026-11-06T15:45:04Z

Weaknesses
  • CWE-1427

    Improper Neutralization of Input Used for LLM Prompting

  • CWE-349

    Acceptance of Extraneous Untrusted Data With Trusted Data