{"total":22,"rows":[{"id":"2605.12015","title":"SkillSafetyBench: Evaluating Agent Safety under Skill-Facing Attack Surfaces","created":"2026-05-12","cited_by_count":19,"area":"agents"},{"id":"2606.23416","title":"Detecting Malicious Agent Skills in the Wild using Attention","created":"2026-06-22","cited_by_count":8,"area":"agents"},{"id":"2606.10749","title":"Toward Secure LLM Agents: Threat Surfaces, Attacks, Defenses, and Evaluation","created":"2026-06-09","cited_by_count":7,"area":"agents"},{"id":"2607.01793","title":"Safety Testing LLM Agents at Scale: From Risk Discovery to Evidence-Grounded Verification","created":"2026-07-02","cited_by_count":7,"area":"agents"},{"id":"2606.02540","title":"SkillHarm: Lifecycle-Aware Skill-Based Attacks via Automated Construction","created":"2026-06-01","cited_by_count":6,"area":"agents"},{"id":"2606.01166","title":"BraveGuard: From Open-World Threats to Safer Computer-Use Agents","created":"2026-05-31","cited_by_count":4,"area":"agents"},{"id":"2605.28201","title":"Plant, Persist, Trigger: Sleeper Attack on Large Language Model Agents","created":"2026-05-27","cited_by_count":3,"area":"agents"},{"id":"2608.16246","title":"CompoSkill: Compositional Skill Chain Attacks from Individually Scanner-Passing LLM Agent Skills","created":"2026-08-17","cited_by_count":3,"area":"agents"},{"id":"2608.25776","title":"EVOMAL: Self-Poisoning in Self-Evolving Coding Agents","created":"2026-08-26","cited_by_count":3,"area":"agents"},{"id":"2607.11751","title":"When Local Monitors Miss Compositional Harm: Diagnosing Distributed Backdoors in Multi-Agent Systems","created":"2026-07-13","cited_by_count":2,"area":"agents"},{"id":"2605.06731","title":"When Routine Chats Turn Toxic: Unintended Long-Term State Poisoning in Personalized Agents","created":"2026-05-07","cited_by_count":1,"area":"agents"},{"id":"2608.19901","title":"MaliciousSkillBench: A Comprehensive Benchmark for Malicious Agent Skill Detection","created":"2026-08-20","cited_by_count":1,"area":"agents"},{"id":"2608.30429","title":"EvoSkill Injection: Red-Teaming Autonomous Skill Generation and Evolution in Self-Evolving Agents","created":"2026-08-31","cited_by_count":1,"area":"agents"},{"id":"2607.24893","title":"Early Detection of Distributed Backdoors in Multi-Agent LLM Systems: A Characterization Study","created":"2026-07-27","cited_by_count":0,"area":"agents"},{"id":"2608.08303","title":"Query-Only Backdoor Attacks on Self-Evolving Skills via Trajectory Poisoning","created":"2026-08-08","cited_by_count":0,"area":"agents"},{"id":"2608.29596","title":"Towards a Systems Foundation for Agentic Skills: Architecture, Lifecycle, and Security","created":"2026-08-30","cited_by_count":0,"area":"agents"},{"id":"2609.13353","title":"SkillAtlas: An Attack Trace Library for Agent Skills","created":"2026-09-11","cited_by_count":0,"area":"agents"},{"id":"2609.36879","title":"SKILLLITE: Evidence-Guided Malicious Skill Auditing with Compact LLMs","created":"2026-09-29","cited_by_count":0,"area":"agents"},{"id":"2609.39352","title":"Hiding in Plain Sight: Decoupling Pretext from Actuation for Skill Poisoning in LLM Agents","created":"2026-09-30","cited_by_count":0,"area":"agents"},{"id":"2609.39607","title":"Pretext: Defeating Malicious Skill Detection Frameworks for AI Agents","created":"2026-09-30","cited_by_count":0,"area":"agents"},{"id":"2610.17727","title":"SkillScreen: High-Recall Screening of Malicious Agent Skills with Decision Models","created":"2026-10-13","cited_by_count":0,"area":"agents"},{"id":"2610.18262","title":"Encrypted Skills Can Become New Security Exploits If AI Agents Know How to Decipher","created":"2026-10-13","cited_by_count":0,"area":"agents"}],"next_cursor":null}