ResearchCode Fingerprints Model-Specific Attribution of LLM-Generated CodearXiv·high signalBeyond binary human-vs-machine: identifies which specific LLM generated a code snippet. For distillation detection and compliance.SourceSource pagearXiv↳ Follow the threadStack layer / Threat patternMitigating Taint-Style MCP Server Vulnerabilities Without Touching Server Code (SPELLSMITH)arXivPolicy dependency / Stack layerReason Less, Verify More: Deterministic Gates Catch a Silent Policy-Violation Failure in Tool-Using AgentsarXivStack layer / Threat patternVEXAIoT: arXiv paper demonstrates autonomous IoT vulnerability exploitation using AI agentsarXivStack layer / Update threadSLBench Finds Up to 70% Unsafe Execution When Codex and Claude Code Follow Logical Relations in Skill FilesarXivStack layer / Threat patternMalaika Grounds Agentic Malware Analysis in Domain, Program Semantics, and Threat IntelarXivStack layer / Threat patternDual-Graph Verification Framework Audits Legacy IT Security Concepts for NIS-2 / OSCAL MigrationarXivStack layer / Follow-up threadLLM Personas Generate Executable Smart-Home Schedules to Replace Privacy-Risky Field DataarXivStack layer / ContrastShared Selective Persistent Memory Lifts Agentic Task Completion to 96% and Cuts Per-Call Token Cost 97xarXiv