{"total":105,"rows":[{"id":"2602.12430","title":"Agent Skills for Large Language Models: Architecture, Acquisition, Security, and the Path Forward","created":"2026-02-12","cited_by_count":113,"area":"agents"},{"id":"2604.08224","title":"Externalization in LLM Agents: A Unified Review of Memory, Skills, Protocols and Harness Engineering","created":"2026-04-09","cited_by_count":74,"area":"agents"},{"id":"2602.08004","title":"Agent Skills: A Data-Driven Analysis of Claude Skills for Extending Large Language Model Functionality","created":"2026-02-08","cited_by_count":72,"area":"agents"},{"id":"2603.04448","title":"SkillNet: Create, Evaluate, and Connect AI Skills","created":"2026-02-26","cited_by_count":53,"area":null},{"id":"2602.06547","title":"\"Do Not Mention This to the User\": Detecting and Understanding Malicious Agent Skills in the Wild","created":"2026-02-06","cited_by_count":50,"area":"agents"},{"id":"2604.03081","title":"Supply-Chain Poisoning Attacks Against LLM Coding Agent Skill Ecosystems","created":"2026-04-03","cited_by_count":45,"area":"agents"},{"id":"2603.29919","title":"SkillReducer: Optimizing LLM Agent Skills for Token Efficiency","created":"2026-03-31","cited_by_count":33,"area":"agents"},{"id":"2604.05172","title":"ClawsBench: Evaluating Capability and Safety of LLM Productivity Agents in Simulated Workspaces","created":"2026-04-06","cited_by_count":33,"area":"agents"},{"id":"2604.04989","title":"SkillAttack: Automated Red Teaming of Agent Skills through Attack Path Refinement","created":"2026-04-05","cited_by_count":30,"area":"agents"},{"id":"2603.11619","title":"Taming OpenClaw: Security Analysis and Mitigation of Autonomous LLM Agent Threats","created":"2026-03-12","cited_by_count":29,"area":"agents"},{"id":"2602.14211","title":"SkillJect: Effectively Automating Skill-Based Prompt Injection for Skill-Enabled Agents","created":"2026-02-15","cited_by_count":25,"area":"agents"},{"id":"2603.00195","title":"Formal Analysis and Supply Chain Security for Agentic AI Skills","created":"2026-02-27","cited_by_count":25,"area":"agents"},{"id":"2603.21019","title":"SkillProbe: Security Auditing for Emerging Agent Skill Marketplaces via Multi-Agent Collaboration","created":"2026-03-22","cited_by_count":21,"area":"agents"},{"id":"2604.04759","title":"Your Agent, Their Asset: A Real-World Safety Analysis of OpenClaw","created":"2026-04-06","cited_by_count":20,"area":"agents"},{"id":"2604.06550","title":"SkillSieve: A Hierarchical Triage Framework for Detecting Malicious AI Agent Skills","created":"2026-04-08","cited_by_count":20,"area":"agents"},{"id":"2604.03070","title":"How Your Credentials Are Leaked by LLM Agent Skills: An Empirical Study","created":"2026-04-03","cited_by_count":19,"area":"agents"},{"id":"2605.12015","title":"SkillSafetyBench: Evaluating Agent Safety under Skill-Facing Attack Surfaces","created":"2026-05-12","cited_by_count":19,"area":"agents"},{"id":"2606.07131","title":"MalSkillBench: A Runtime-Verified Benchmark of Malicious Agent Skills","created":"2026-06-05","cited_by_count":19,"area":"agents"},{"id":"2606.00448","title":"When Safe Skills Collide: Measuring Compositional Risk in Agent Skill Ecosystems","created":"2026-05-30","cited_by_count":17,"area":"agents"},{"id":"2604.24026","title":"From Skill Text to Skill Structure: The Scheduling-Structural-Logical Representation for Agent Skills","created":"2026-04-27","cited_by_count":16,"area":"agents"},{"id":"2604.02837","title":"Towards Secure Agent Skills: Architecture, Threat Taxonomy, and Security Analysis","created":"2026-04-03","cited_by_count":13,"area":"agents"},{"id":"2604.08407","title":"Your Agent Is Mine: Measuring Malicious Intermediary Attacks on the LLM Supply Chain","created":"2026-04-09","cited_by_count":13,"area":"agents"},{"id":"2605.11418","title":"Under the Hood of SKILL.md: Semantic Supply-chain Attacks on AI Agent Skill Registry","created":"2026-05-12","cited_by_count":12,"area":null},{"id":"2605.13940","title":"AgentTrap: Measuring Runtime Trust Failures in Third-Party Agent Skills","created":"2026-05-13","cited_by_count":12,"area":"agents"},{"id":"2603.16572","title":"Context Matters: Repository-Aware Security Analysis of the Agent Skill Ecosystem","created":"2026-03-17","cited_by_count":11,"area":null},{"id":"2607.02357","title":"Cloak and Detonate: Scanner Evasion and Dynamic Detection of Agent Skill Malware","created":"2026-07-02","cited_by_count":10,"area":"agents"},{"id":"2606.26524","title":"VIGIL: Runtime Enforcement of Behavioral Specifications in AI Agent Skills","created":"2026-06-25","cited_by_count":9,"area":"agents"},{"id":"2603.19974","title":"Trojan's Whisper: Stealthy Manipulation of OpenClaw through Injected Bootstrapped Guidance","created":"2026-03-20","cited_by_count":8,"area":"agents"},{"id":"2604.22888","title":"RouteGuard: Internal-Signal Detection of Skill Poisoning in LLM Agents","created":"2026-04-24","cited_by_count":7,"area":"agents"},{"id":"2604.25109","title":"Structured Security Auditing and Robustness Enhancement for Untrusted Agent Skills","created":"2026-04-28","cited_by_count":7,"area":null},{"id":"2605.02900","title":"Safety in Embodied AI: A Survey of Risks, Attacks, and Defenses","created":"2026-03-28","cited_by_count":7,"area":"safety"},{"id":"2605.14460","title":"Exploiting LLM Agent Supply Chains via Payload-less Skills","created":"2026-05-14","cited_by_count":6,"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":"2606.14502","title":"From Chatbot to Digital Colleague: The Paradigm Shift Toward Persistent Autonomous AI","created":"2026-06-12","cited_by_count":6,"area":null},{"id":"2606.32025","title":"Generative Skill Composition for LLM Agents","created":"2026-06-30","cited_by_count":6,"area":"agents"},{"id":"2607.01456","title":"From Anatomy to Smells: An Empirical Study of SKILL.md in Agent Skills","created":"2026-07-01","cited_by_count":6,"area":"agents"},{"id":"2607.10113","title":"Dynamic Agent Skills: A Lifecycle Survey and Taxonomy of Evolving Skill Libraries","created":"2026-07-11","cited_by_count":6,"area":"agents"},{"id":"2603.27204","title":"MalSkills: Detecting Malicious Skills in the Agentic Supply Chain via Neuro-symbolic Reasoning","created":"2026-03-28","cited_by_count":5,"area":"lr"},{"id":"2605.05868","title":"SkillScope: Toward Fine-Grained Least-Privilege Enforcement for Agent Skills","created":"2026-05-07","cited_by_count":5,"area":"agents"},{"id":"2605.23989","title":"Towards trustworthy agentic AI: a comprehensive survey of safety, robustness, privacy, and system security","created":"2026-05-17","cited_by_count":5,"area":"agents"},{"id":"2606.14154","title":"SkillMutator: Benchmarking and Defending Language-and-Code Cross-modal Attacks on LLM Agent Skills","created":"2026-06-12","cited_by_count":5,"area":"agents"},{"id":"2606.18198","title":"Seeing Is Not Screening: Multimodal Hidden Instruction Attacks on Agent Skill Scanners","created":"2026-06-16","cited_by_count":5,"area":"agents"},{"id":"2607.13987","title":"Agent Skill Security: Threat Models, Attacks, Defenses, and Evaluation","created":"2026-07-15","cited_by_count":5,"area":"agents"},{"id":"2604.15709","title":"Bilevel Optimization of Agent Skills via Monte Carlo Tree Search","created":"2026-04-17","cited_by_count":4,"area":"agents"},{"id":"2608.09732","title":"ColluSkill: Adversarial Cross-Skill Composition for Evading Agent Skill Scanners","created":"2026-08-10","cited_by_count":4,"area":"agents"},{"id":"2602.16653","title":"Agent Skill Framework: Perspectives on the Potential of Small to Medium Language Models in Industrial Environments","created":"2026-02-18","cited_by_count":3,"area":"agents"},{"id":"2606.01567","title":"Defenses & Enablers For Skill Injection Attacks on Terminal Based Agents","created":"2026-06-01","cited_by_count":3,"area":"agents"},{"id":"2606.11671","title":"Runtime Skill Audit: Targeted Runtime Probing for Agent Skill Security","created":"2026-06-10","cited_by_count":3,"area":"agents"},{"id":"2607.01136","title":"Skills Are Not Islands: Measuring Dependency and Risk in Agent Skill Supply Chains","created":"2026-07-01","cited_by_count":3,"area":"agents"},{"id":"2607.20121","title":"OpenSkillRisk: Benchmarking Agent Safety When Using Real-World Risky Third-Party Skills","created":"2026-07-22","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":"2606.20636","title":"SkillHarness: Harnessing Safe Skills for Computer-Use Agents","created":"2026-06-02","cited_by_count":2,"area":"agents"},{"id":"2607.00911","title":"From Registry to Repository: How AI Agent Skills Are Written, Adapted, and Maintained","created":"2026-07-01","cited_by_count":2,"area":"agents"},{"id":"2607.02345","title":"SkillFuzz: Fuzzing Skill Composition for Implicit Intents Discovery in Open Skill Marketplaces","created":"2026-07-02","cited_by_count":2,"area":null},{"id":"2607.21824","title":"Protocol-Level Attacks on Agentic Commerce Platforms: A Cross-Platform Taxonomy, AIP-Bench, and Unified Defense","created":"2026-07-23","cited_by_count":2,"area":"agents"},{"id":"2608.04192","title":"Behavioral Skill Reconstruction: Reconstructing Hidden Functionality from LLM Agent Skills","created":"2026-08-04","cited_by_count":2,"area":"agents"},{"id":"2609.00065","title":"Scientific Agent Skills: A Library of Procedural Knowledge for Research Agents","created":"2026-08-30","cited_by_count":2,"area":"agents"},{"id":"2602.02584","title":"Constitutional Spec-Driven Development: Enforcing Security by Construction in AI-Assisted Code Generation","created":"2026-01-31","cited_by_count":1,"area":null},{"id":"2604.24657","title":"AgentWard: A Lifecycle Security Architecture for Autonomous AI Agents","created":"2026-04-27","cited_by_count":1,"area":"agents"},{"id":"2605.25435","title":"Security of OpenClaw Agents: Fundamentals, Attacks, and Countermeasures","created":"2026-05-25","cited_by_count":1,"area":"agents"},{"id":"2605.25815","title":"Behind EvoMap: Characterizing a Self-Evolving Agent-to-Agent Collaboration Network","created":"2026-05-25","cited_by_count":1,"area":null},{"id":"2607.03220","title":"CONTRA: Red-Teaming Configurations of Personalizable Agents","created":"2026-07-03","cited_by_count":1,"area":"agents"},{"id":"2607.03238","title":"An Empirical Study of Downstream Adaptation for Agent Skills","created":"2026-07-03","cited_by_count":1,"area":"agents"},{"id":"2607.09065","title":"Inside the Skill Market: From Software Engineering Activities to Reusable Agent Skills","created":"2026-07-10","cited_by_count":1,"area":null},{"id":"2607.10534","title":"Cross-Layer Misalignment Detection in Agent Skills: A Progressive Loading-Aware Contrastive Learning Approach","created":"2026-07-12","cited_by_count":1,"area":"agents"},{"id":"2608.02683","title":"$S^3$: Improving Agent Safety through Multi-Stage Defense","created":"2026-08-03","cited_by_count":1,"area":"agents"},{"id":"2608.05204","title":"SkillTrace: Multi-Trace Provenance Auditing for LLM-Agent Skill Reuse","created":"2026-08-05","cited_by_count":1,"area":"agents"},{"id":"2608.07639","title":"SkillConsist: Detecting Inconsistencies in Agent Skills via Bidirectional Graph Alignment","created":"2026-08-07","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":"2609.05920","title":"Versioned Transitive Dependency-Closure Binding and Operation-Time Effect Governance for Agent Skills: ClosureBound","created":"2026-09-05","cited_by_count":1,"area":null},{"id":"2609.29543","title":"Safe Skill Retirement for Physical Agents","created":"2026-08-25","cited_by_count":1,"area":null},{"id":"2610.07645","title":"SkillPoison: Progressive Skill Poisoning via Successful Experiences","created":"2026-10-06","cited_by_count":1,"area":"agents"},{"id":"2604.16753","title":"Know When to Trust the Skill: Delayed Appraisal and Epistemic Vigilance for Single-Agent LLMs","created":"2026-04-17","cited_by_count":0,"area":"lr"},{"id":"2604.27358","title":"Safe Bilevel Delegation (SBD): A Formal Framework for Runtime Delegation Safety in Multi-Agent Systems","created":"2026-04-30","cited_by_count":0,"area":"agents"},{"id":"2605.09038","title":"SearchSkill: Teaching LLMs to Use Search Tools with Evolving Skill Banks","created":"2026-05-09","cited_by_count":0,"area":null},{"id":"2606.06752","title":"Pomona: Continuous Code Quality Improvement via Small, Agentic Pull Requests at Bloomberg","created":"2026-06-04","cited_by_count":0,"area":"agents"},{"id":"2606.07992","title":"VATS: Exploiting Implicit Authority in Error-Path Injection via Systematic Mutation","created":"2026-06-06","cited_by_count":0,"area":"agents"},{"id":"2606.21071","title":"Local LLM Agents as Vulnerable Runtimes:A Source-Code Audit of the Agent Runtime Layer","created":"2026-06-19","cited_by_count":0,"area":"agents"},{"id":"2607.12340","title":"Skills That Don't Exist: A Large-Scale Study of Hallucinated Skill Recommendation in LLM Agents","created":"2026-07-14","cited_by_count":0,"area":"agents"},{"id":"2607.25890","title":"Distributing Security Controls Through Harness Engineering","created":"2026-07-28","cited_by_count":0,"area":"agents"},{"id":"2608.00104","title":"Skillsets on the Chain: A Blockchain-based Zero-Trust Framework for Agentic AI Networking","created":"2026-07-31","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":"2608.09577","title":"ElasticBack: Stealthy Conditional Backdoor in LLM-Agent Skills via Coupled Trigger-Rule Optimization","created":"2026-08-10","cited_by_count":0,"area":"agents"},{"id":"2608.16544","title":"VCE-Skill: Enhancing Skill Self-Evolution with Version-Change Experience","created":"2026-08-17","cited_by_count":0,"area":null},{"id":"2608.17588","title":"TRUSS: Towards Task-Reliable and User-Safe Automated Agent Skill Generation","created":"2026-08-18","cited_by_count":0,"area":null},{"id":"2608.21929","title":"SkillBloat: Token Amplification Attacks via Skill Injection in LLM Coding Agents","created":"2026-08-22","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":"2609.01487","title":"Defense-as-Skill: Evolving Runtime Guard Skill for Skill-Augmented Agents","created":"2026-09-01","cited_by_count":0,"area":null},{"id":"2609.06052","title":"SkillSpec: Intent-Masked Specification Reasoning for Agent Skill Correctness","created":"2026-09-05","cited_by_count":0,"area":null},{"id":"2609.13353","title":"SkillAtlas: An Attack Trace Library for Agent Skills","created":"2026-09-11","cited_by_count":0,"area":"agents"},{"id":"2609.14079","title":"SkillSecurer: Detecting and Patching Prompt-Injection Vulnerabilities in AI Agent Skills","created":"2026-09-12","cited_by_count":0,"area":"agents"},{"id":"2609.17274","title":"After the Party: Growth, Governance, and Security Scanning in the OpenClaw Agent Skill Ecosystem","created":"2026-09-15","cited_by_count":0,"area":null},{"id":"2609.29454","title":"Demystifying Agent Skills for Smart Contract Auditing: Design, Effectiveness, Behavioral Impact","created":"2026-09-24","cited_by_count":0,"area":"agents"},{"id":"2609.30383","title":"Stealth Apart, Harm Together: Skill Cascading Attacks on Skill-Based Agent Systems","created":"2026-09-24","cited_by_count":0,"area":"agents"},{"id":"2609.35912","title":"MMSkillRisk: Can Agents Stay Safe When Multimodal Skills Become Traps?","created":"2026-09-28","cited_by_count":0,"area":"agents"},{"id":"2609.39450","title":"ActionGuard: Tool Call Authorization under Poisoned Skills","created":"2026-09-30","cited_by_count":0,"area":"agents"},{"id":"2610.05943","title":"Runaway Reaction: When Benign Skills Compose into Malicious Behavior","created":"2026-10-05","cited_by_count":0,"area":null},{"id":"2610.06001","title":"AgentSpy: Making AI Agent Behavior Observable","created":"2026-10-05","cited_by_count":0,"area":"agents"},{"id":"2610.06950","title":"Learning to Decide, Not to Reason: Parameter-Efficient Decision Operators via Low-Rank Activation Steering","created":"2026-10-03","cited_by_count":0,"area":"lr"}],"next_cursor":"100"}