arXiv AI
AgentTrap: Stateful Feedback Deception against Autonomous Penetration Testing Agents
Read the original on arXiv AI →The Flow has not summarised this story yet — read it at arXiv AI.
Related stories
arXiv AI
Jun 16
MUZZLE: Adaptive Agentic Red-Teaming of Web Agents Against Indirect Prompt Injection Attacks
arXiv:2602. 09222v2 Announce Type: replace-cross Abstract: Large language model (LLM) based web agents are increasingly deployed to automate complex online tasks by directly interacting with web sites and performing actions on users' behalf.
arXiv Machine Learning
Jul 30
AgentSnare: Learning to Delay, Divert, and Defuse Autonomous Penetration Agents
arXiv:2607. 26998v1 Announce Type: cross Abstract: Large language model (LLM) agents automate penetration testing through an observation-action loop, selecting actions based on observations returned by tools.
arXiv Computation and Language
Oct 26
Honeyquest for LLMs: Rethinking Cyber Deception for AI Attackers
arXiv:2606.21037v3 Announce Type: replace-cross Abstract: The empirical foundation of cyber deception relies on human-centered hypotheses, but the rapid emergence of autonomous, AI-enabled attackers...
arXiv AI
Jul 23
Know Your Agent: Reconnaissance-Driven Pentesting of AI Agents
arXiv:2607. 19837v1 Announce Type: new Abstract: Traditional pentesting uses reconnaissance at each step to uncover unseen weaknesses, build stronger attacks, and advance the objective; we argue that AI agents require the same treatment.
Hugging Face Trending Papers
Jun 24
Decoupling Reconnaissance and Exploitation: Measuring the Capability Boundaries of LLM-Based Web Penetration Testing
Large Language Models (LLMs) have shown promise for automated penetration testing, yet existing end-to-end black-box evaluations are highly susceptible to error cascading: failures in early reconnaissance can mask an agent's actual ability to exploit vulnerabilities. To more accurately characterize these capabilities, we propose a two-stage decoupled evaluation framework that separates exploit execution from reconnaissance.
arXiv AI
Jun 19
Analyzing Defensive Misdirection Against Model-Guided Automated Attacks on Agentic AI Systems
arXiv:2606. 20470v1 Announce Type: cross Abstract: Agentic AI systems increasingly rely on language-model components to interpret instructions, process external data, invoke tools, and coordinate with other agents.