137 matches found
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! π 2026.08 Paper is...
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...
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...
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...
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...
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...
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...
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...
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...
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...
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 ...
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...
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...
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 andβ¦
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...
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...
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,...
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...
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...
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...
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...