PREVIEW. This is how it will look in an inbox; it was not sent to you. Each real email carries its own unsubscribe link and Keryn's postal address. KERYN HEADLINES Weekly, week 8 of 2026 Retrospective Covers 10 February 2026 12:00 to 17 February 2026 12:00 UTC Web: https://keryn.dev/headlines/weekly/2026-W08/ TOP DEVELOPMENTS [1] Google patches first Chrome zero-day exploited in attacks this year BleepingComputer · Advisory · https://bleepingcomputer.com/news/security/google-patches-first-chrome-zero-day-exploited-in-attacks-this-year [2] CISA gives feds 3 days to patch actively exploited BeyondTrust flaw BleepingComputer · Advisory · https://bleepingcomputer.com/news/security/cisa-orders-feds-to-patch-beyondtrust-flaw-within-three-days [3] Microsoft February 2026 Patch Tuesday fixes 6 zero-days, 58 flaws BleepingComputer · Advisory · https://bleepingcomputer.com/news/microsoft/microsoft-february-2026-patch-tuesday-fixes-6-zero-days-58-flaws [4] CISA flags critical Microsoft SCCM flaw as exploited in attacks BleepingComputer · Incident · https://bleepingcomputer.com/news/security/cisa-flags-microsoft-configmgr-rce-flaw-as-exploited-in-attacks [5] Critical BeyondTrust RCE flaw now exploited in attacks, patch now BleepingComputer · Incident · https://bleepingcomputer.com/news/security/critical-beyondtrust-rce-flaw-now-exploited-in-attacks-patch-now SAST [6] AXE: Grey-Box Exploitability Confirmation for Localized Vulnerability Reports arXiv · Research · https://arxiv.org/abs/2602.14345 [7] VulReaD: Knowledge-Graph-guided Software Vulnerability Reasoning and Detection arXiv · Research · https://arxiv.org/abs/2602.10787 [8] SecCodePRM: A Process Reward Model for Code Security arXiv · Research · https://arxiv.org/abs/2602.10418 [9] QRS: A Rule-Synthesizing Neuro-Symbolic Triad for Autonomous Vulnerability Discovery arXiv · Research · https://arxiv.org/abs/2602.09774 SCA [10] Lazarus Campaign Plants Malicious Packages in npm and PyPI Ecosystems The Hacker News · Incident · https://thehackernews.com/2026/02/lazarus-campaign-plants-malicious.html [11] Weight space Detection of Backdoors in LoRA Adapters arXiv · Research · https://arxiv.org/abs/2602.15195 [12] Overthinking Loops in Agents: A Structural Risk via MCP Tools arXiv · Research · https://arxiv.org/abs/2602.14798 [13] SkillJect: Effectively Automating Skill-Based Prompt Injection for Skill-Enabled Agents arXiv · Research · https://arxiv.org/abs/2602.14211 DAST [14] Following Dragons: Code Review-Guided Fuzzing arXiv · Research · https://arxiv.org/abs/2602.10487 [15] GPU-Fuzz: Finding Memory Errors in Deep Learning Frameworks arXiv · Research · https://arxiv.org/abs/2602.10478 AGENTIC SDLC [16] An end-to-end agentic pipeline for smart contract translation and quality evaluation arXiv · Research · https://arxiv.org/abs/2602.13808 [17] Assessing Spear-Phishing Website Generation in Large Language Model Coding Agents arXiv · Research · https://arxiv.org/abs/2602.13363 [18] Agentic Knowledge Distillation: Autonomous Training of Small Language Models for SMS Threat Detection arXiv · Research · https://arxiv.org/abs/2602.10869 [19] SWE-MiniSandbox: Container-Free Reinforcement Learning for Building Software Engineering Agents arXiv · Research · https://arxiv.org/abs/2602.11210 REMEDIATION [20] Microsoft Patch Tuesday matches last year’s zero-day high with six actively exploited vulnerabilities CyberScoop · Advisory · https://cyberscoop.com/microsoft-patch-tuesday-february-2026 [21] Apple fixes zero-day flaw used in 'extremely sophisticated' attacks BleepingComputer · Analysis · https://bleepingcomputer.com/news/security/apple-fixes-zero-day-flaw-used-in-extremely-sophisticated-attacks [22] Over 60 Software Vendors Issue Security Fixes Across OS, Cloud, and Network Platforms The Hacker News · Analysis · https://thehackernews.com/2026/02/over-60-software-vendors-issue-security.html [23] Windows 11 KB5077181 fixes boot failures linked to failed updates BleepingComputer · Analysis · https://bleepingcomputer.com/news/microsoft/windows-11-kb5077181-fixes-boot-failures-linked-to-failed-updates TRUST [24] Passwords to passkeys: Staying ISO 27001 compliant in a passwordless era BleepingComputer · Standard / policy · https://bleepingcomputer.com/news/security/passwords-to-passkeys-staying-iso-27001-compliant-in-a-passwordless-era [25] Why ‘secure-by-design’ systems are non-negotiable in the AI era CyberScoop · Analysis · https://cyberscoop.com/data-center-security-ai-infrastructure-investment-op-ed [26] Building the ethical AI framework of the future: from philosophy to practice arXiv · Research · https://arxiv.org/abs/2603.06599 [27] ForesightSafety Bench: A Frontier Risk Evaluation and Governance Framework towards Safe AI arXiv · Research · https://arxiv.org/abs/2602.14135 MODELS [28] Google says hackers are abusing Gemini AI for all attacks stages BleepingComputer · Research · https://bleepingcomputer.com/news/security/google-says-hackers-are-abusing-gemini-ai-for-all-attacks-stages [29] Exploiting Layer-Specific Vulnerabilities to Backdoor Attack in Federated Learning arXiv · Research · https://arxiv.org/abs/2602.15161 [30] Boundary Point Jailbreaking of Black-Box LLMs arXiv · Research · https://arxiv.org/abs/2602.15001 [31] AI Safety Evaluations Need To Consider Cascading Effects arXiv · Research · https://arxiv.org/abs/2603.00088 AI SECURITY [32] Manipulating AI memory for profit: The rise of AI Recommendation Poisoning Microsoft · Research · https://microsoft.com/en-us/security/blog/2026/02/10/ai-recommendation-poisoning [33] MCPShield: A Security Cognition Layer for Adaptive Trust Calibration in Model Context Protocol Agents arXiv · Research · https://arxiv.org/abs/2602.14281 [34] When Benchmarks Lie: Evaluating Malicious Prompt Classifiers Under True Distribution Shift arXiv · Research · https://arxiv.org/abs/2602.14161 [35] AlignSentinel: Alignment-Aware Detection of Prompt Injection Attacks arXiv · Research · https://arxiv.org/abs/2602.13597 ADVISORIES IN THIS WINDOW 56 npm advisories · 42 critical · 2 high · 11 moderate · 1 low 24 Go advisories · 1 critical · 7 high · 13 moderate · 3 low 9 PyPI advisories · 1 critical · 4 high · 2 moderate · 2 low 9 crates.io advisories · 4 critical · 2 high · 2 moderate · 1 low 7 Packagist advisories · 1 critical · 2 high · 4 moderate 7 Maven advisories · 1 critical · 2 high · 3 moderate · 1 low 1 NuGet advisory · 1 high All advisories: https://keryn.dev/headlines/advisories/ Titles, links and short excerpts only; every item links to its source. Preview: the unsubscribe link and Keryn's postal address are added to each email when it is sent.