ResearchSlowBA: Efficiency Backdoor Attacks on GUI AgentsarXiv·high signalNovel attack targeting agent efficiency not correctness. Triggers cause excessive reasoning steps. Agents work correctly but become unusably slow.SourceSource pagearXiv↳ Follow the threadStack layer / Threat patternDistributed Backdoors Prove Per-Step Agent Monitors Can Be Right on Every Step and Still Miss the AttackarXivPolicy dependency / Threat patternNew Paper 'aiAuthZ' Moves Agent Authorization Off-Host, Reports 0% Residual Attack Across 15 LLMsarXivStack layer / Threat patternStudy of 44 Developers: AI Code Assistants Barely Improve Secure API UsagearXivStack layer / Threat patternBackendForge: Best Coding Agent (GPT-5.5) Deploys Correct Backends Only 28.6% of the Time Under a Strict OraclearXivThreat pattern'Agent Hacks Agent': Automated Red-Teaming Loop Builds a Reusable Vulnerability Concept Graph for LLM AgentsarXivPolicy dependency / Threat patternNetInjectBench: Naive Network-Ops Agents Take Unsafe Actions 82.5% of the Time Under Prompt InjectionarXivStack layer / Threat patternMako: A 'Self-Evolving Agentic OS' That Writes New Exploits Against Live Targets and Hot-Loads Them Into ItselfarXivStack layer / Threat patternAgentLens: Open-Source Benchmark Scores the Whole Coding-Agent Trajectory, Not Just Pass/FailarXiv