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 Monthly, February 2026 Retrospective Covers February 2026 Web: https://keryn.dev/headlines/monthly/2026-02/ 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] 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 [3] CISA flags critical SolarWinds RCE flaw as exploited in attacks BleepingComputer · Incident · https://bleepingcomputer.com/news/security/cisa-flags-critical-solarwinds-rce-flaw-as-actively-exploited [4] CISA: Recently patched RoundCube flaws now exploited in attacks BleepingComputer · Advisory · https://bleepingcomputer.com/news/security/cisa-recently-patched-roundcube-flaws-now-exploited-in-attacks [5] CISA orders feds to patch actively exploited Dell flaw within 3 days BleepingComputer · Advisory · https://bleepingcomputer.com/news/security/cisa-orders-feds-to-patch-actively-exploited-dell-flaw-within-3-days [6] Critical SolarWinds Serv-U flaws offer root access to servers BleepingComputer · Analysis · https://bleepingcomputer.com/news/security/critical-solarwinds-serv-u-flaws-offer-root-access-to-servers [7] Detecting backdoored language models at scale Microsoft · Incident · https://microsoft.com/en-us/security/blog/2026/02/04/detecting-backdoored-language-models-at-scale [8] CISA warns of five-year-old GitLab flaw exploited in attacks BleepingComputer · Incident · https://bleepingcomputer.com/news/security/cisa-warns-of-five-year-old-gitlab-flaw-exploited-in-attacks [9] 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 [10] 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 SAST [11] Enhancing Continual Learning for Software Vulnerability Prediction: Addressing Catastrophic Forgetting via Hybrid-Confidence-Aware Selective Replay for Temporal LLM Fine-Tuning arXiv · Research · https://arxiv.org/abs/2602.23834 [12] Automated Vulnerability Detection in Source Code Using Deep Representation Learning arXiv · Research · https://arxiv.org/abs/2602.23121 [13] Automatic, Expressive, and Scalable Fuzzing with Stitching arXiv · Research · https://arxiv.org/abs/2602.18689 [14] AXE: Grey-Box Exploitability Confirmation for Localized Vulnerability Reports arXiv · Research · https://arxiv.org/abs/2602.14345 [15] VulReaD: Knowledge-Graph-guided Software Vulnerability Reasoning and Detection arXiv · Research · https://arxiv.org/abs/2602.10787 SCA [16] Hackers exploit critical React Native Metro bug to breach dev systems BleepingComputer · Incident · https://bleepingcomputer.com/news/security/hackers-exploit-critical-react-native-metro-bug-to-breach-dev-systems [17] Join Us at Open Source SecurityCon Europe 2026 in Amsterdam OpenSSF · Analysis · https://openssf.org/blog/2026/02/03/join-us-at-open-source-securitycon-europe-2026-in-amsterdam [18] Malicious StripeApi NuGet Package Mimicked Official Library and Stole API Tokens The Hacker News · Incident · https://thehackernews.com/2026/02/malicious-stripeapi-nuget-package.html [19] Malicious NuGet Packages Stole ASP.NET Data; npm Package Dropped Malware The Hacker News · Incident · https://thehackernews.com/2026/02/malicious-nuget-packages-stole-aspnet.html [20] Cline CLI 2.3.0 Supply Chain Attack Installed OpenClaw on Developer Systems The Hacker News · Incident · https://thehackernews.com/2026/02/cline-cli-230-supply-chain-attack.html DAST [21] Towards the Systematic Testing of Regular Expression Engines arXiv · Research · https://arxiv.org/abs/2603.00311 [22] LLM-Powered Silent Bug Fuzzing in Deep Learning Libraries via Versatile and Controlled Bug Transfer arXiv · Research · https://arxiv.org/abs/2602.23065 [23] ICSSPulse: A Modular LLM-Assisted Platform for Industrial Control System Penetration Testing arXiv · Research · https://arxiv.org/abs/2602.20663 [24] FuzzySQL: Uncovering Hidden Vulnerabilities in DBMS Special Features with LLM-Driven Fuzzing arXiv · Research · https://arxiv.org/abs/2602.19490 [25] Trustworthy AI LLM Scalability Risk Index (LSRI): A Cybersecurity Framework Assessing Agentic-AI Security & Software Model Supply Chain Safety Boosting AI-Generated Malware Defense & Explainability Mitigating Emerging Risks of Generative AI arXiv · Research · https://arxiv.org/abs/2602.19021 AGENTIC SDLC [26] RoguePilot Flaw in GitHub Codespaces Enabled Copilot to Leak GITHUB_TOKEN The Hacker News · Incident · https://thehackernews.com/2026/02/roguepilot-flaw-in-github-codespaces.html [27] ThreatsDay Bulletin: OpenSSL RCE, Foxit 0-Days, Copilot Leak, AI Password Flaws & 20+ Stories The Hacker News · Incident · https://thehackernews.com/2026/02/threatsday-bulletin-openssl-rce-foxit-0.html [28] ClarEval: A Benchmark for Evaluating Clarification Skills of Code Agents under Ambiguous Instructions arXiv · Research · https://arxiv.org/abs/2603.00187 [29] Claude Code Flaws Allow Remote Code Execution and API Key Exfiltration The Hacker News · Research · https://thehackernews.com/2026/02/claude-code-flaws-allow-remote-code.html [30] AdapTools: Adaptive Tool-based Indirect Prompt Injection Attacks on Agentic LLMs arXiv · Research · https://arxiv.org/abs/2602.20720 AI-BOM [31] Permissive-Washing in the Open AI Supply Chain: A Large-Scale Audit of License Integrity arXiv · Research · https://arxiv.org/abs/2602.08816 REMEDIATION [32] 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 [33] 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 [34] Third-Party Patching and the Business Footprint We All Share BleepingComputer · Analysis · https://bleepingcomputer.com/news/security/third-party-patching-and-the-business-footprint-we-all-share [35] Formal Analysis and Supply Chain Security for Agentic AI Skills arXiv · Research · https://arxiv.org/abs/2603.00195 [36] Trend Micro warns of critical Apex One code execution flaws BleepingComputer · Analysis · https://bleepingcomputer.com/news/security/trend-micro-warns-of-critical-apex-one-rce-vulnerabilities TRUST [37] EU Cyber Resilience Act (CRA) in Practice @ FOSDEM 2026: From Awareness to Action OpenSSF · Standard / policy · https://openssf.org/blog/2026/02/17/eu-cyber-resilience-act-cra-in-practice-fosdem-2026-from-awareness-to-action [38] 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 [39] Lifecycle-Integrated Security for AI-Cloud Convergence in Cyber-Physical Infrastructure arXiv · Research · https://arxiv.org/abs/2602.23397 [40] Agent Behavioral Contracts: Formal Specification and Runtime Enforcement for Reliable Autonomous AI Agents arXiv · Research · https://arxiv.org/abs/2602.22302 [41] Right to History: A Sovereignty Kernel for Verifiable AI Agent Execution arXiv · Research · https://arxiv.org/abs/2602.20214 MODELS [42] MIDAS: Multi-Image Dispersion and Semantic Reconstruction for Jailbreaking MLLMs arXiv · Research · https://arxiv.org/abs/2603.00565 [43] Pragma-VL: Towards a Pragmatic Arbitration of Safety and Helpfulness in MLLMs arXiv · Research · https://arxiv.org/abs/2603.13292 [44] ROKA: Robust Knowledge Unlearning against Adversaries arXiv · Research · https://arxiv.org/abs/2603.00436 [45] Jailbreak Foundry: From Papers to Runnable Attacks for Reproducible Benchmarking arXiv · Research · https://arxiv.org/abs/2602.24009 [46] Assessing Deanonymization Risks with Stylometry-Assisted LLM Agent arXiv · Research · https://arxiv.org/abs/2602.23079 AI SECURITY [47] ClawJacked Flaw Lets Malicious Sites Hijack Local OpenClaw AI Agents via WebSocket The Hacker News · Incident · https://thehackernews.com/2026/02/clawjacked-flaw-lets-malicious-sites.html [48] From Goals to Aspects, Revisited: An NFR Pattern Language for Agentic AI Systems arXiv · Research · https://arxiv.org/abs/2603.00472 [49] AESP: A Human-Sovereign Economic Protocol for AI Agents with Privacy-Preserving Settlement arXiv · Research · https://arxiv.org/abs/2603.00318 [50] From Leaky Thoughts to Private Reasoning: Controlling What LRMs Say to Themselves arXiv · Research · https://arxiv.org/abs/2602.24210 [51] AgentSentry: Mitigating Indirect Prompt Injection in LLM Agents via Temporal Causal Diagnostics and Context Purification arXiv · Research · https://arxiv.org/abs/2602.22724 ADVISORIES IN THIS WINDOW 508 npm advisories · 300 critical · 105 high · 86 moderate · 17 low 147 Go advisories · 13 critical · 58 high · 63 moderate · 13 low 110 PyPI advisories · 15 critical · 36 high · 49 moderate · 10 low 90 Packagist advisories · 5 critical · 33 high · 43 moderate · 9 low 40 Maven advisories · 4 critical · 10 high · 15 moderate · 11 low 39 crates.io advisories · 10 critical · 11 high · 15 moderate · 3 low 39 NuGet advisories · 9 high · 24 moderate · 6 low 11 RubyGems advisories · 8 high · 2 moderate · 1 low 4 Multi-ecosystem advisories · 2 critical · 1 high · 1 moderate 3 GitHub Actions advisories · 1 high · 2 moderate 1 Swift advisory · 1 moderate 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.