cloudrasp-log4j2

CloudArmor · Модуль самозащиты приложений во время выполнения — версия Log4j2 Китайский упрощённый Этот проект является локальной версией CloudArmor, специально созданной для защиты от Log4j2 CVE-2021-44228. Для работы этого проекта не требуется подключение к сети. Пожалуйста, ПРОВЕДИТЕ...

Persona Guardrail: A Production-Grade Defense Framework for Agentic Systems

Large language model-based agents are increasingly deployed to perform domain-specific tasks by interacting with enterprise knowledge, tools, and external services. Existing runtime guardrails primarily target prompt injection and other attack-specific behaviors under a black-box threat model, bu...

HARDE: Optimizing Agent Harnesses for Runtime Risk Detection and Execution Control

Large language model LLM agents are vulnerable to safety risks such as injected malicious instructions or misleading information, motivating runtime defenses that prevent unsafe action in execution across diverse risks while preserving benign-task utility. Existing system-level defenses either...

Before Acting, Change the State: Prospective State Intervention for Web Agents under Deceptive Interfaces

LLM-based Web agents can autonomously complete user tasks, yet deceptive interfaces can steer them toward outcomes that conflict with users' interests. Existing defenses primarily intervene on agent behavior through blocking, guidance, or replanning. We identify a distinct failure mode: a...

Beyond Handcrafted Security: Towards Self-Evolving Defense for LLM Agents

The expanding operational capabilities of large language model LLM agents introduce sophisticated security threats. Runtime defenses have emerged as an effective approach to mitigating these risks by integrating security mechanisms into the agent execution loop. However, existing runtime defenses...

AttriGuard: Defeating Indirect Prompt Injection in LLM Agents Via Causal Attribution of Tool Invocations

LLM agents are highly vulnerable to Indirect Prompt Injection IPI, where adversaries embed malicious directives in untrusted tool outputs to hijack execution. Most existing defenses treat IPI as an input-level semantic discrimination problem, which often fails to generalize to unseen payloads. We...

When Bots Take the Bait: Exposing and Mitigating the Emerging Social Engineering Attack in Web Automation Agent

Web agents, powered by large language models LLMs, are increasingly deployed to automate complex web interactions. The rise of open-source frameworks e.g., Browser Use, Skyvern-AI has accelerated adoption, but also broadened the attack surface. While prior research has focused on model threats su...

XLM + AMSI: New runtime defense against Excel 4.0 macro malware

We have recently expanded the integration of Antimalware Scan Interface AMSI with Office 365 to include the runtime scanning of Excel 4.0 XLM macros, to help antivirus solutions tackle the increase in attacks that use malicious XLM macros. This integration, an example of the many security feature...