The paper introduces ExploitGym, a large-scale benchmark, demonstrating that advanced AI agents can successfully turn theoretical software vulnerabilities into working exploits, highlighting growing c…

The paper systematically maps LLM agent vulnerabilities by testing 10,000 prompt variations, finding that 'goal reframing' language is the primary trigger for exploitation, rather than broad adversari…

FORGE is a multi-agent system that integrates vulnerability exploitation, prioritization, and detection engineering into a single pipeline, achieving high-fidelity, multi-level exploitation and genera…

The paper introduces AgentSecBench, a security evaluation framework that measures prompt injection, privacy leakage, and tool-use integrity in LLM agents by defining formal security games and testing…

The paper reports on penetration tests conducted on proprietary, large-scale AI agent systems, finding that security vulnerabilities persist despite stricter development standards.

The paper introduces BenchJack, an automated red-teaming system that systematically audits popular AI agent benchmarks, revealing numerous reward-hacking exploits and demonstrating a method to signifi…

VIPER-MCP is a novel, end-to-end automated framework that detects and dynamically confirms the exploitability of taint-style vulnerabilities in Model Context Protocol (MCP) servers, achieving high-fid…

The paper introduces SEC-bench Pro, a rigorous benchmark for evaluating LLM-based bug hunting on complex software, finding that even advanced agents struggle with long-horizon security tasks.

The paper introduces a novel, practical evaluation protocol that shifts the assessment of AI pentesting agents from simple task completion to validated, open-ended vulnerability discovery in complex,…

This paper conducts a large-scale empirical study demonstrating that Java library exploits can accurately identify affected versions, achieving high recall and precision, and proposes strategies for e…

The paper introduces a multi-dimensional evasion framework and a new benchmark (A3S-Bench) to test autonomous agents, demonstrating that stateful, multi-turn attacks significantly increase system risk…

The paper introduces CyberGym-E2E, a large-scale, end-to-end benchmark designed to comprehensively evaluate AI agents' capabilities across the entire lifecycle of real-world software vulnerability dis…

SAILOR automates the construction of symbolic execution harnesses by combining static analysis and LLM-based synthesis, significantly improving the scalability and effectiveness of vulnerability disco…

The paper introduces MOSAIC-Bench, a benchmark demonstrating that coding agents can ship exploitable code by complying with seemingly innocuous, staged tasks, a vulnerability that is not easily mitiga…

Automation-Exploit is a multi-agent LLM framework that enables adaptive offensive security by using a digital twin to safely test and execute high-risk memory-corruption exploits on live targets.

The paper systematically evaluates six OpenClaw-series AI agent frameworks, demonstrating that these agentized systems possess significant security vulnerabilities that are distinct from and more seve…

SecureForge is an automated pipeline that significantly reduces cybersecurity vulnerabilities in LLM-generated code by optimizing system prompts, achieving up to a 48% reduction in output vulnerabilit…

The paper re-evaluates LLM agents on CTFs, finding that while general-purpose agents like claude-code are strong baselines, specialized, modular architectures significantly improve performance and con…

This paper identifies and characterizes 'guidance injection,' a stealthy attack vector that embeds adversarial operational narratives into autonomous coding agents' bootstrap guidance, demonstrating h…

The paper introduces RAVEN, a Retrieval-Augmented Vulnerability Exploration Network, which uses LLM agents and RAG to automatically generate comprehensive, structured vulnerability analysis reports fo…