Lucene search
+L

137 matches found

Kitploit
Kitploit
β€’added 2026/11/18 8:26 p.m.β€’26 views

batch_jailbreak

Official Repo for Safety in Batches? Understanding and Mitigating Safety Failures in Batch Prompting Kihyun Kim, Hee-Seon Kim, Wonjun Lee, Changick Kim Korea Advanced Institute of Science and Technology KAIST News 2026.09 Our paper has been accepted to AACL-IJCNLP 2026 Main! πŸŽ‰ 2026.08 Paper is...

6.1AI score
SaveExploits0References1
NVD
NVD
β€’added 2026/11/06 3:17 p.m.β€’12 views

CVE-2026-106020

Improper neutralization of input used for LLM prompting vulnerability in Johnson Controls EasyIO Neo IO Manager and Tools Installer allows Search Order Hijacking. This issue affects EasyIO Neo IO Manager and Tools Installer: 1.1.0.0...

8.6CVSS0.00127EPSS
SaveExploits0References1
NVD
NVD
β€’added 2026/11/06 2:17 p.m.β€’18 views

CVE-2026-123653

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...

7.5CVSS0.00215EPSS
SaveExploits0References10
Cvelist
Cvelist
β€’added 2026/11/06 2:04 p.m.β€’31 views

CVE-2026-106020

Improper neutralization of input used for LLM prompting vulnerability in Johnson Controls EasyIO Neo IO Manager and Tools Installer allows Search Order Hijacking. This issue affects EasyIO Neo IO Manager and Tools Installer: 1.1.0.0...

8.6CVSS0.00127EPSS
SaveExploits0References1
Vulnrichment
Vulnrichment
β€’added 2026/11/06 2:04 p.m.β€’6 views

CVE-2026-106020

Improper neutralization of input used for LLM prompting vulnerability in Johnson Controls EasyIO Neo IO Manager and Tools Installer allows Search Order Hijacking. This issue affects EasyIO Neo IO Manager and Tools Installer: 1.1.0.0...

8.6CVSS6AI score0.00127EPSS
SaveExploits0References1
EUVD
EUVD
β€’added 2026/11/06 2:04 p.m.β€’14 views

EUVD-2026-118264

Improper neutralization of input used for LLM prompting vulnerability in Johnson Controls EasyIO Neo IO Manager and Tools Installer allows Search Order Hijacking. This issue affects EasyIO Neo IO Manager and Tools Installer: 1.1.0.0...

8.6CVSS6AI score0.00127EPSS
SaveExploits0References1
CVE
CVE
β€’added 2026/11/06 2:04 p.m.β€’22 views

CVE-2026-106020

Johnson Controls EasyIO Neo IO Manager and Tools Installer version 1.1.0.0 are affected by an Improper Neutralization of Input Used for LLM Prompting vulnerability (CWE-1427). This flaw allows for Search Order Hijacking . The vulnerability is associated with a CVSS 4.0 score of 8.6 (High) , where...

8.6CVSS6AI score0.00127EPSS
SaveExploits0References1
osv_cve
osv_cve
β€’added 2026/11/06 1:30 p.m.β€’11 views

CVE-2026-123653 esengine DeepSeek-Reasonix doc.go discoverDocs llm prompting input

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...

5.3CVSS5.2AI score
SaveExploits0References12
Mend
Mend
β€’added 2026/11/06 1:30 p.m.β€’5 views

CVE-2026-123653

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...

7.5CVSS5.8AI score0.00215EPSS
SaveExploits0References12
Vulnrichment
Vulnrichment
β€’added 2026/11/06 1:30 p.m.β€’5 views

CVE-2026-123653 esengine DeepSeek-Reasonix doc.go discoverDocs llm prompting input

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...

7.5CVSS5.8AI score0.00215EPSS
SaveExploits0References10
CVE
CVE
β€’added 2026/11/06 1:30 p.m.β€’28 views

CVE-2026-123653

The esengine DeepSeek-Reasonix software (versions up to 2.52.0 ) is vulnerable to a remote attack due to improper neutralization of input used for LLM prompting . The flaw is located in the discoverDocs function within the internal/memory/doc.go file. This vulnerability allows for the acceptance ...

7.5CVSS5.8AI score0.00215EPSS
SaveExploits0References10
Cvelist
Cvelist
β€’added 2026/11/06 1:30 p.m.β€’29 views

CVE-2026-123653 esengine DeepSeek-Reasonix doc.go discoverDocs llm prompting input

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...

7.5CVSS0.00215EPSS
SaveExploits0References10
EUVD
EUVD
β€’added 2026/11/06 1:30 p.m.β€’14 views

EUVD-2026-118237

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...

7.5CVSS5.8AI score0.00215EPSS
SaveExploits0References10
Rapid7 Vulnerability Database (full)
Rapid7 Vulnerability Database (full)
β€’added 2026/11/06 12:00 a.m.β€’11 views

CVE-2026-106020: Johnson Controls EasyIO Neo IO Manager and Tools Installer: Improper neutralization of input used for LLM prompting vulnerability in Johnson Controls EasyIO Neo IO Manager and…

Improper neutralization of input used for LLM prompting vulnerability in Johnson Controls EasyIO Neo IO Manager and Tools Installer allows Search Order Hijacking. This issue affects EasyIO Neo IO Manager and Tools Installer: 1.1.0.0...

8.6CVSS6.1AI score0.00127EPSS
SaveExploits0References1
Rapid7 Vulnerability Database (full)
Rapid7 Vulnerability Database (full)
β€’added 2026/11/06 12:00 a.m.β€’10 views

CVE-2026-123653: esengine DeepSeek-Reasonix: A security vulnerability has been detected in esengine DeepSeek-Reasonix up to 2.52.0

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...

7.5CVSS5.9AI score0.00215EPSS
SaveExploits0References2
Packet Storm News
Packet Storm News
β€’added 2026/10/29 12:00 a.m.β€’20 views

Systematic Evaluation of Adversarial Jailbreaking Attacks and Defenses across Seven Large Language Models

Large language models LLMs deployed in safety-critical settings must resist adversarial inputs designed to elicit harmful outputs. We present a systematic empirical evaluation of five adversarial jailbreaking attack families---direct requests, roleplay-based jailbreaking, hypothetical framing,...

5.9AI score
SaveExploits0
NVD
NVD
β€’added 2026/10/28 8:17 p.m.β€’36 views

CVE-2026-115415

Improper neutralization of input used for LLM prompting in the environment tool in Strands Agents Tools before 0.8.6 might allow remote actors to obtain the agent host's environment variables in cleartext, including cloud credentials and API keys, via a crafted prompt that disables the tool's...

6.5CVSS0.00343EPSS
SaveExploits0References3
EUVD
EUVD
β€’added 2026/10/28 7:33 p.m.β€’22 views

EUVD-2026-112407

Improper neutralization of input used for LLM prompting in the environment tool in Strands Agents Tools before 0.8.6 might allow remote actors to obtain the agent host's environment variables in cleartext, including cloud credentials and API keys, via a crafted prompt that disables the tool's...

6.5CVSS6.1AI score0.00343EPSS
SaveExploits0References3
Mend
Mend
β€’added 2026/10/28 7:33 p.m.β€’16 views

CVE-2026-115415

Improper neutralization of input used for LLM prompting in the environment tool in Strands Agents Tools before 0.8.6 might allow remote actors to obtain the agent host's environment variables in cleartext, including cloud credentials and API keys, via a crafted prompt that disables the tool's...

6.5CVSS6.1AI score0.00343EPSS
SaveExploits0References3
Positive Technologies
Positive Technologies
β€’added 2026/10/28 12:00 a.m.β€’35 views

PT-2026-129166

Name of the Vulnerable Software and Affected Versions Strands Agents Tools versions prior to 0.8.6 Description Improper neutralization of input used for LLM prompting in the environment tool allows remote actors to obtain the agent host's environment variables in cleartext, including cloud...

6.5CVSS5.9AI score0.00343EPSS
SaveExploits0References8
Rows per page
Query Builder