{"total":72,"rows":[{"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":"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":"2604.11790","title":"ClawGuard: A Runtime Security Framework for Tool-Augmented LLM Agents Against Indirect Prompt Injection","created":"2026-04-13","cited_by_count":27,"area":"agents"},{"id":"2605.15338","title":"Hidden in Memory: Sleeper Memory Poisoning in LLM Agents","created":"2026-05-14","cited_by_count":27,"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":"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":"2605.03378","title":"ARGUS: Defending LLM Agents Against Context-Aware Prompt Injection","created":"2026-05-05","cited_by_count":14,"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":"2605.28914","title":"AIRGuard: Guarding Agent Actions with Runtime Authority Control","created":"2026-05-27","cited_by_count":13,"area":"agents"},{"id":"2606.15242","title":"Benign in Isolation, Harmful in Composition: Security Risks in Agent Skill Ecosystems","created":"2026-06-13","cited_by_count":13,"area":"agents"},{"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":"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":"2606.11435","title":"Agent Skill Evaluation and Evolution: Frameworks and Benchmarks","created":"2026-06-09","cited_by_count":8,"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":"2604.22888","title":"RouteGuard: Internal-Signal Detection of Skill Poisoning in LLM Agents","created":"2026-04-24","cited_by_count":7,"area":"agents"},{"id":"2605.11770","title":"Behavioral Integrity Verification for AI Agent Skills","created":"2026-05-12","cited_by_count":7,"area":"agents"},{"id":"2606.07943","title":"Poise: Position-Aware One-Instruction Skill Injection for Silent Execution on LLM Agents","created":"2026-06-06","cited_by_count":7,"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":"2604.09443","title":"Many-Tier Instruction Hierarchy in LLM Agents","created":"2026-04-10","cited_by_count":6,"area":"agents"},{"id":"2606.01317","title":"SABER: Benchmarking Operational Safety of LLM Coding Agents in Stateful Project Workspaces","created":"2026-05-31","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":"2606.03024","title":"SkillGuard: A Permission-Centric Framework for Agent Skill Security","created":"2026-06-02","cited_by_count":6,"area":"agents"},{"id":"2606.19191","title":"PhantomSkill: Malicious Code Injection in Agent Skill Ecosystems","created":"2026-06-17","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":"2605.05868","title":"SkillScope: Toward Fine-Grained Least-Privilege Enforcement for Agent Skills","created":"2026-05-07","cited_by_count":5,"area":"agents"},{"id":"2605.09594","title":"Trust Me, Import This: Dependency Steering Attacks via Malicious Agent Skills","created":"2026-05-10","cited_by_count":5,"area":"agents"},{"id":"2605.13044","title":"No Attack Required: Semantic Fuzzing for Specification Violations in Agent Skills","created":"2026-05-13","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":"2603.22447","title":"Latent Reuse in Agent Skills: Multi-modal Clone Detection at Ecosystem Scale","created":"2026-03-23","cited_by_count":4,"area":"agents"},{"id":"2605.31042","title":"From Prompt Injection to Persistent Control: Defending Agentic Harness Against Trojan Backdoors","created":"2026-05-29","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":"2605.28201","title":"Plant, Persist, Trigger: Sleeper Attack on Large Language Model Agents","created":"2026-05-27","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":"2607.25619","title":"SkillGate: Cost Efficient Runtime Malicious Skill File Detection in Coding Agents","created":"2026-07-28","cited_by_count":3,"area":"agents"},{"id":"2608.12851","title":"Practice Makes Unsafe: Skill Misevolution in Self-Improving LLM Agents","created":"2026-08-13","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":"2605.08460","title":"When Child Inherits: Modeling and Exploiting Subagent Spawn in Multi-Agent Networks","created":"2026-05-08","cited_by_count":2,"area":"agents"},{"id":"2605.11047","title":"Red-Teaming Agent Execution Contexts: Open-World Security Evaluation on OpenClaw","created":"2026-05-11","cited_by_count":2,"area":"agents"},{"id":"2607.09016","title":"SLBench: Evaluating How LLM Agents Follow Logical Relations in Skills","created":"2026-07-10","cited_by_count":2,"area":"agents"},{"id":"2608.05563","title":"When Experience Becomes Instruction: Trajectory Poisoning in Self-Evolving Agent Skill Systems","created":"2026-08-06","cited_by_count":2,"area":"agents"},{"id":"2606.02302","title":"SeClaw: Spec-Driven Security Task Synthesis for Evaluating Autonomous Agents","created":"2026-06-01","cited_by_count":1,"area":"agents"},{"id":"2606.20631","title":"Harnessing Agent Skills: Architectural Patterns and a Reference Architecture for Skill-Mediated LLM Agents","created":"2026-05-29","cited_by_count":1,"area":"agents"},{"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":"2608.07639","title":"SkillConsist: Detecting Inconsistencies in Agent Skills via Bidirectional Graph Alignment","created":"2026-08-07","cited_by_count":1,"area":"agents"},{"id":"2608.08453","title":"What Keeps Agent Skills from Being Reusable? Evidence from 138K SKILL.md Files","created":"2026-08-09","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":"2608.03485","title":"SkillSentry: Adaptive Honey Worlds for Dynamic Safety Testing of Agent Skills","created":"2026-08-04","cited_by_count":0,"area":"agents"},{"id":"2608.06862","title":"SynChain: Inducing Computer-Use Agent Systems to Construct Their Own Attack Chains","created":"2026-08-07","cited_by_count":0,"area":"agents"},{"id":"2608.08264","title":"OBLIVION: Workflow-Level Operational Skill Unlearning for Deployed Agents","created":"2026-08-08","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":"2608.21101","title":"ClawSentry: A Progressive Multi-Tier Security Monitor for Safeguarding Autonomous LLM Agents","created":"2026-08-21","cited_by_count":0,"area":"agents"},{"id":"2608.30441","title":"ECLIPSE: Self-Evolving Stealthy Prompt Injection Attack against Long-Horizon Agentic Systems","created":"2026-08-31","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":"2609.14079","title":"SkillSecurer: Detecting and Patching Prompt-Injection Vulnerabilities in AI Agent Skills","created":"2026-09-12","cited_by_count":0,"area":"agents"},{"id":"2609.28585","title":"Persistent Billable State: Denial-of-Wallet Attacks and Defenses in Tool-Calling LLM Agents","created":"2026-09-23","cited_by_count":0,"area":"agents"},{"id":"2609.30266","title":"LLM Agents Can Easily Tamper With Their Own Traces","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":"2609.39065","title":"Can Agents Trust Their Skills? Uncovering Unsafe Chains of Trust in Skill-Based LLM Agents","created":"2026-09-30","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":"2610.06001","title":"AgentSpy: Making AI Agent Behavior Observable","created":"2026-10-05","cited_by_count":0,"area":"agents"},{"id":"2610.06966","title":"APEX: Active Protection at Execution Boundaries for LLM Agents","created":"2026-10-03","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}