OverAct: Measuring and Mitigating Proactive Over-Authorization in LLM Tool-Calling Agents

LLM agents with tool-calling capabilities can access external services and private user data, but they may retrieve more information than a user's request explicitly requires. We study this behavior in structured tool-calling agents and term it proactive over-authorization. This setting differs...

OpenShell

!IMPORTANT New in OpenShell 0.1.x: a stable release cadence, new isolation primitives, an expanded extension surface, and new APIs. Read the 0.1.0 upgrade guide. OpenShell is the safe, private runtime for fleets of autonomous AI agents. Agents are most useful when they can read files, install...

CVE-2026-51872

Devika v1.0 is vulnerable to Code Injection via the Runner.runcode function in src/agents/runner/runner.py...

Responsible-Alliance-Protocol

Protocolo de Delimitación Teleológica TBP v4.2.1 Una capa de aplicación de políticas y auditoría criptográfica para agentes de IA autónomos. TBP bloquea clases específicas de acciones de agentes —transferencias financieras autónomas, acceso a sistemas de control industrial, integración con sistem...

ActGuard

ActGuard ActGuard es una defensa de auditoría de acciones previa a la ejecución contra la inyección indirecta de prompts en agentes LLM que utilizan herramientas. Este repositorio contiene la implementación final de ActGuard y el entorno de ejecución basado en AgentDojo necesario para evaluarla. ...

CYBERDUDEBIVASH-ServiceNow-AI-Agent-Audit-Script

CYBERDUDEBIVASH Script de Auditoría de Agentes AI de ServiceNow v1.1 Enero 2026 Asegura tu Futuro con IA – Herramienta de Auditoría de Nivel Empresarial con Actualizaciones 2026 Este script audita Agentes AI de ServiceNow en busca de vulnerabilidades como CVE-2025-12420, brechas de gobernanza y...

Defenses-for-Tool-Integrated-LLM

Defensas universales para agentes LLM integrados con herramientas contra ataques adversarios Este repositorio contiene el código y los experimentos de nuestro proyecto sobre la defensa de agentes de modelos de lenguaje de gran tamaño LLM integrados con herramientas contra ataques adversarios...

No One Architecture Fits All: A Cross-Environment Evaluation of Hierarchical Red Team Agents

Autonomous red team agents increasingly stress-test AI-enabled cyber defenses by planning strategy and executing multistage attacks. Reinforcement learning RL and large language models LLMs offer complementary mechanisms for the planning and execution such agents require, and prior work has...

AuraForge: Scaling Security Supervision for Training Coding Agents

Coding agents are now proficient enough to generate complex software applications from a single prompt. As their capabilities have grown, human oversight has increasingly shifted from line-by-line code review toward hands-off evaluation of outcomes. However, recent studies have shown that such a...

CVE-2026-51871

Devika v1.0 is vulnerable to Code Injection in the Runner.execute function in src/agents/runner/runner.py which allows an attacker to achieve arbitrary code execution by exploiting the direct execution of LLM-generated content...

Memetic Trojans: Social Contagions As Carriers of Adversarial Payloads in Agent Networks

Autonomous large language model LLM agents increasingly interact in network environments where adversarial content can propagate between agents. Known attacks include agent worms, which spread through self-replicating prompt injections or configuration compromises. We introduce memetic trojans, a...

Can Agents Trust Their Skills? Uncovering Unsafe Chains of Trust in Skill-Based LLM Agents

LLM agents increasingly rely on installable skills, which are packages of instructions, code, and resources that equip them with task-specific capabilities and, once installed, can be automatically invoked across subsequent user tasks. This creates a chain of trust in which users delegate authori...

CVE-2026-51871

Devika v1.0 is vulnerable to Code Injection in the Runner.execute function in src/agents/runner/runner.py which allows an attacker to achieve arbitrary code execution by exploiting the direct execution of LLM-generated content...

APTInvestBench: Evaluating Autonomous APT Investigation under Varying Telemetry

Large language model LLM agents could help security operations centers SOCs investigate advanced persistent threats APTs by turning weak leads into evidence for intrusion scoping and response. Yet success under one telemetry setting does not establish robustness to changes in log collection,...

ZoneClaw: Mitigating Persistent Memory Attacks by Establishing Memory-Zoning in OpenClaw-Style Computer-Use Agents

Computer-use agents increasingly operate as long-running assistants through persistent workspace memory, which OpenClaw-style CUAs realize as automatically reloaded files that hold user instructions, system summaries, and external claims at the same privilege level. Here, remembering a claim...

EUVD-2026-90411

Devika v1.0 is vulnerable to Code Injection via the Runner.runcode function in src/agents/runner/runner.py...

From A2A Attacks to Envelope-Layer Defense: Red-Teaming Evaluation of LLM Agents and a Three-Layer Isomorphic Attack-Defense Model

Agent interaction protocols such as ACP and A2A have moved LLM-based agents toward multi-agent collaboration, introducing new security threats. A task sent by a remote peer over A2A is treated as a legitimate request, providing a natural channel for indirect prompt injection. Existing agent...

Sapien: A Stateful Policy Engine for Autonomous AI Agents

Contextual security defenses prevent AI agents from taking rogue actions by synthesizing a task-specific policy and enforcing it on the agent's tool calls. In multi-step tasks, however, which actions are valid often depends on what the agent has already done and learned. We present Sapien, a poli...

RedTeamSimmer

RedTeamSimmer La interfaz que siempre has querido para Atomic Red Team Una plataforma de emulación de adversarios basada en web y orquestación de pruebas de Atomic Red Team. Descripción general RedTeamSimmer es una plataforma de emulación de adversarios de código abierto basada en web que...

guardskill

GuardSkill A repository can make your coding agent run code the moment it opens the folder. GuardSkill checks for that before you do. npx guardskill . Read-only. No network calls, no telemetry, no configuration, no account, no dependencies. It reads git configuration and hook scripts, prints what...