SourcesState of AI Agent Security 2026: 88% Report IncidentsGravitee.io·high signalGravitee.io report: 88% incidents, 14.4% security approval, 45.6% shared API keysSourceSource pageGravitee.io↳ Follow the threadPolicy dependency / Stack layerCynative Ships an Open-Source Deep-Research Security Agent With Default-Deny Write PermissionsIT Security NewsStack layer / Threat patternStudy of 44 Developers: AI Code Assistants Barely Improve Secure API UsagearXivStack layer / Threat patternOpenAI Ships GPT-5.6 Family (Sol/Terra/Luna) to API and Codex, Claims +13.1 on Agents' Last Exam vs Claude Fable 5OpenAIStack layer / Threat pattern'Friendly Fire': AI Now PoC Tricks Claude Code and Codex Into Running README-Planted MalwareAI Now Institute (via The Hacker News)Stack layer / Threat patternCISA Warns Russian State Hackers Are Targeting Home and Office RoutersArs TechnicaPolicy dependency / Stack layerGoogle Hit With Another AI-Training Copyright Suit From Major PublishersTechCrunchThreat pattern / Update threadAgent Skills for .NET reaches stable GA with human-in-the-loop approval by defaultMicrosoft Agent Framework BlogStack layer / Threat patternBackendForge: Best Coding Agent (GPT-5.5) Deploys Correct Backends Only 28.6% of the Time Under a Strict OraclearXiv