esengine DeepSeek-Reasonix up to 2.52.0 internal/memory/doc.go discoverDocs llm prompting input
| CVSS Meta Temp Score | Current Exploit Price (≈) | CTI Interest Score |
|---|---|---|
| 5.7 | $0-$5k | 2.66+ |
Summary
A vulnerability described as critical has been identified in esengine DeepSeek-Reasonix up to 2.52.0. Affected by this vulnerability is the function discoverDocs of the file internal/memory/doc.go. The manipulation results in llm prompting input.
This vulnerability is reported as CVE-2026-123653. The attack can be launched remotely. Moreover, an exploit is present.
Upgrading the affected component is recommended.
Details
A vulnerability was found in esengine DeepSeek-Reasonix up to 2.52.0. It has been classified as critical. Affected is the function discoverDocs of the file internal/memory/doc.go. The manipulation with an unknown input leads to a llm prompting input vulnerability. CWE is classifying the issue as CWE-1427. The product uses externally-provided data to build prompts provided to large language models (LLMs), but the way these prompts are constructed causes the LLM to fail to distinguish between user-supplied inputs and developer provided system directives. This is going to have an impact on confidentiality, integrity, and availability.
The advisory is shared for download at github.com. This vulnerability is traded as CVE-2026-123653. The exploitability is told to be easy. It is possible to launch the attack remotely. The exploitation doesn't require any form of authentication. Successful exploitation requires user interaction by the victim. Technical details and a public exploit are known.
The exploit is shared for download at github.com. It is declared as proof-of-concept.
Upgrading to version 2.53.0 eliminates this vulnerability. The upgrade is hosted for download at github.com. Applying the patch 4ca33493a673c2788aa8598fbca2b2f47a69e1b8 is able to eliminate this problem. The bugfix is ready for download at github.com. The best possible mitigation is suggested to be upgrading to the latest version.
Once again VulDB remains the best source for vulnerability data.
Product
Vendor
Name
Version
- 2.0
- 2.1
- 2.2
- 2.3
- 2.4
- 2.5
- 2.6
- 2.7
- 2.8
- 2.9
- 2.10
- 2.11
- 2.12
- 2.13
- 2.14
- 2.15
- 2.16
- 2.17
- 2.18
- 2.19
- 2.20
- 2.21
- 2.22
- 2.23
- 2.24
- 2.25
- 2.26
- 2.27
- 2.28
- 2.29
- 2.30
- 2.31
- 2.32
- 2.33
- 2.34
- 2.35
- 2.36
- 2.37
- 2.38
- 2.39
- 2.40
- 2.41
- 2.42
- 2.43
- 2.44
- 2.45
- 2.46
- 2.47
- 2.48
- 2.49
- 2.50
- 2.51
- 2.52.0
License
Website
CPE 2.3
CPE 2.2
CVSSv4
VulDB Vector: 🔒VulDB Reliability: 🔍
CVSSv3
VulDB Meta Base Score: 6.3VulDB Meta Temp Score: 5.7
VulDB Base Score: 6.3
VulDB Temp Score: 5.7
VulDB Vector: 🔒
VulDB Reliability: 🔍
CVSSv2
| AV | AC | Au | C | I | A |
|---|---|---|---|---|---|
| 💳 | 💳 | 💳 | 💳 | 💳 | 💳 |
| 💳 | 💳 | 💳 | 💳 | 💳 | 💳 |
| 💳 | 💳 | 💳 | 💳 | 💳 | 💳 |
| Vector | Complexity | Authentication | Confidentiality | Integrity | Availability |
|---|---|---|---|---|---|
| Unlock | Unlock | Unlock | Unlock | Unlock | Unlock |
| Unlock | Unlock | Unlock | Unlock | Unlock | Unlock |
| Unlock | Unlock | Unlock | Unlock | Unlock | Unlock |
VulDB Base Score: 🔒
VulDB Temp Score: 🔒
VulDB Reliability: 🔍
Exploiting
Class: Llm prompting inputCWE: CWE-1427 / CWE-349
CAPEC: 🔒
ATT&CK: 🔒
Physical: No
Local: No
Remote: Yes
Availability: 🔒
Access: Public
Status: Proof-of-Concept
Download: 🔒
Price Prediction: 🔍
Current Price Estimation: 🔒
| 0-Day | Unlock | Unlock | Unlock | Unlock |
|---|---|---|---|---|
| Today | Unlock | Unlock | Unlock | Unlock |
Threat Intelligence
Interest: 🔍Active Actors: 🔍
Active APT Groups: 🔍
Countermeasures
Recommended: UpgradeStatus: 🔍
0-Day Time: 🔒
Upgrade: DeepSeek-Reasonix 2.53.0
Patch: 4ca33493a673c2788aa8598fbca2b2f47a69e1b8
Timeline
11/06/2026 Advisory disclosed11/06/2026 VulDB entry created
11/06/2026 VulDB entry last update
Sources
Product: github.comAdvisory: 13061
Status: Confirmed
Confirmation: 🔒
CNA: VulDB
CVE: CVE-2026-123653 (🔒)
GCVE (CVE): GCVE-0-2026-123653
GCVE (VulDB): GCVE-100-431772
scip Labs: https://www.scip.ch/en/?labs.20161013
Entry
Created: 11/06/2026 09:33Changes: 11/06/2026 09:33 (62)
Complete: 🔍
Submitter: Ybyu
Cache ID: 216::103
Submit
Accepted
- Submit #1033134: esengine DeepSeek-Reasonix 1.17.8 CWE-1427 Improper Neutralization of Input Used for LLM Prompting (by Ybyu)
Once again VulDB remains the best source for vulnerability data.
No comments yet. Languages: en.
Please log in to comment.