{"total":61,"rows":[{"id":"2107.03374","title":"Evaluating Large Language Models Trained on Code","created":"2021-07-07","cited_by_count":8320,"area":null},{"id":"2601.10338","title":"Agent Skills in the Wild: An Empirical Study of Security Vulnerabilities at Scale","created":"2026-01-15","cited_by_count":105,"area":"agents"},{"id":"2406.10279","title":"We Have a Package for You! A Comprehensive Analysis of Package Hallucinations by Code Generating LLMs","created":"2024-06-12","cited_by_count":65,"area":null},{"id":"2601.17548","title":"Prompt Injection Attacks on Agentic Coding Assistants: A Systematic Analysis of Vulnerabilities in Skills, Tools, and Protocol Ecosystems","created":"2026-01-24","cited_by_count":31,"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":"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":"2606.07131","title":"MalSkillBench: A Runtime-Verified Benchmark of Malicious Agent Skills","created":"2026-06-05","cited_by_count":19,"area":"agents"},{"id":"2604.05485","title":"Auditable Agents","created":"2026-04-07","cited_by_count":15,"area":"agents"},{"id":"2403.15600","title":"Just another copy and paste? Comparing the security vulnerabilities of ChatGPT generated code and StackOverflow answers","created":"2024-03-22","cited_by_count":13,"area":null},{"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":"2308.04898","title":"An Empirical Study on Using Large Language Models to Analyze Software Supply Chain Security Failures","created":"2023-08-09","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":"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":"2606.07943","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":"2403.12196","title":"Leveraging Large Language Models to Detect npm Malicious Packages","created":"2024-03-18","cited_by_count":6,"area":null},{"id":"2605.14460","title":"Exploiting LLM Agent Supply Chains via Payload-less Skills","created":"2026-05-14","cited_by_count":6,"area":"agents"},{"id":"2606.01494","title":"ClawHub Security Signals: When VirusTotal, Static Analysis, and SkillSpector Disagree","created":"2026-05-31","cited_by_count":6,"area":null},{"id":"2505.19532","title":"Fox in the Henhouse: Supply-Chain Backdoor Attacks Against Reinforcement Learning","created":"2025-05-26","cited_by_count":5,"area":"deeprl"},{"id":"2509.07941","title":"ImportSnare: Directed \"Code Manual\" Hijacking in Retrieval-Augmented Code Generation","created":"2025-09-09","cited_by_count":5,"area":"rag"},{"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":"2607.13987","title":"Agent Skill Security: Threat Models, Attacks, Defenses, and Evaluation","created":"2026-07-15","cited_by_count":5,"area":"agents"},{"id":"2209.07957","title":"Malicious Source Code Detection Using Transformer","created":"2022-09-16","cited_by_count":4,"area":null},{"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":"2504.13769","title":"Detecting Malicious Source Code in PyPI Packages with LLMs: Does RAG Come in Handy?","created":"2025-04-18","cited_by_count":3,"area":"rag"},{"id":"2508.15987","title":"PickleBall: Secure Deserialization of Pickle-based Machine Learning Models (Extended Report)","created":"2025-08-21","cited_by_count":3,"area":null},{"id":"2603.11862","title":"You Told Me to Do It: Measuring Instructional Text-induced Private Data Leakage in LLM Agents","created":"2026-03-12","cited_by_count":3,"area":"agents"},{"id":"2603.26221","title":"Clawed and Dangerous: Can We Trust Open Agentic Systems?","created":"2026-03-27","cited_by_count":3,"area":"agents"},{"id":"2606.26924","title":"A Deterministic Control Plane for LLM Coding Agents","created":"2026-06-25","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":"2504.17198","title":"Automatically Generating Rules of Malicious Software Packages via Large Language Model","created":"2025-04-24","cited_by_count":2,"area":null},{"id":"2509.06703","title":"On the (In)Security of Loading Machine Learning Models","created":"2025-09-08","cited_by_count":2,"area":null},{"id":"2509.24408","title":"FuncPoison: Poisoning Function Library to Hijack Multi-agent Autonomous Driving Systems","created":"2025-09-29","cited_by_count":2,"area":"driving"},{"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":"2505.08842","title":"LibVulnWatch: A Deep Assessment Agent System and Leaderboard for Uncovering Hidden Vulnerabilities in Open-Source AI Libraries","created":"2025-05-13","cited_by_count":1,"area":"agents"},{"id":"2601.12148","title":"Many Hands Make Light Work: An LLM-based Multi-Agent System for Detecting Malicious PyPI Packages","created":"2026-01-17","cited_by_count":1,"area":"agents"},{"id":"2602.19818","title":"SafePickle: Robust and Generic ML Detection of Malicious Pickle-based ML Models","created":"2026-02-23","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":"2605.03309","title":"Cryptographic Registry Provenance: Structural Defense Against Dependency Confusion in AI Package Ecosystems","created":"2026-05-05","cited_by_count":1,"area":null},{"id":"2606.13757","title":"SEVRA-BENCH: Social Engineering of Vulnerabilities in Review Agents","created":"2026-06-11","cited_by_count":1,"area":"agents"},{"id":"2609.10350","title":"Cyber-Financial Contagion: Modeling the Propagation of an AI Vendor Compromise Through the Banking System","created":"2026-09-09","cited_by_count":1,"area":null},{"id":"2510.14778","title":"Leveraging Code Cohesion Analysis to Identify Source Code Supply Chain Attacks","created":"2025-10-16","cited_by_count":0,"area":null},{"id":"2601.06838","title":"CHASE: LLM Agents for Dissecting Malicious PyPI Packages","created":"2026-01-11","cited_by_count":0,"area":"agents"},{"id":"2604.22768","title":"Secure On-Premise Deployment of Open-Weights Large Language Models in Radiology: An Isolation-First Architecture with Prospective Pilot Evaluation","created":"2026-03-25","cited_by_count":0,"area":null},{"id":"2604.26219","title":"eDySec: A Deep Learning-based Explainable Dynamic Analysis Framework for Detecting Malicious Packages in PyPI Ecosystem","created":"2026-04-29","cited_by_count":0,"area":null},{"id":"2605.20368","title":"Security Document Classification with a Fine-Tuned Local Large Language Model: Benchmark Data and an Open-Source System","created":"2026-05-19","cited_by_count":0,"area":null},{"id":"2606.19023","title":"Lifecycle-Aware Dynamic Analysis for Secure ML Model Execution","created":"2026-06-17","cited_by_count":0,"area":null},{"id":"2606.24402","title":"Poisoned Playbooks: Demystifying Knowledge Poisoning Effects on AI Security Agents","created":"2026-06-23","cited_by_count":0,"area":"rag"},{"id":"2606.26866","title":"Fortress and Gatekeeper: Theorizing Transitive Trust in Third-Party Cybersecurity Risk Governance","created":"2026-06-25","cited_by_count":0,"area":null},{"id":"2607.03350","title":"LLM-Enhanced Hierarchical Heterogeneous Graph Representation Learning for Malicious Python Package Detection","created":"2026-07-03","cited_by_count":0,"area":null},{"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":"2607.17550","title":"(A)iSpy: Parasitic Trojans for Machine Learning Infrastructure","created":"2026-07-20","cited_by_count":0,"area":"safety"},{"id":"2607.24888","title":"Trusting-Trust Attack against an Entire Linux Distribution through Binary Manipulation","created":"2026-07-27","cited_by_count":0,"area":"safety"},{"id":"2608.08468","title":"SkillsMetric: Mapping the Detection Boundary of Static Analysis for Malicious Agent Skills","created":"2026-08-09","cited_by_count":0,"area":"agents"},{"id":"2608.31142","title":"Auditing Anonymous AI Models: A Four-Stage Protocol for Black-Box Identity Verification","created":"2026-08-31","cited_by_count":0,"area":null},{"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":"2609.31282","title":"Resource-Optimized and Energy-Aware Agentic AI Framework Anchored on Blockchain for Secure Software Supply Chains","created":"2026-09-25","cited_by_count":0,"area":null},{"id":"2609.35889","title":"SINGED: Correct Outputs Do Not Certify Safe Execution in LLM Agents","created":"2026-09-27","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":"2610.05139","title":"Hidden in the Comments: A Context-Injection Attack Surface in Code LLMs","created":"2026-10-04","cited_by_count":0,"area":null},{"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"}],"next_cursor":null}