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 9 of 2026 Retrospective Covers 17 February 2026 12:00 to 24 February 2026 12:00 UTC Web: https://keryn.dev/headlines/weekly/2026-W09/ TOP DEVELOPMENTS [1] 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 [2] 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 [3] 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 [4] 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 [5] Malicious npm Packages Harvest Crypto Keys, CI Secrets, and API Tokens The Hacker News · Research · https://thehackernews.com/2026/02/malicious-npm-packages-harvest-crypto.html SAST [6] Automatic, Expressive, and Scalable Fuzzing with Stitching arXiv · Research · https://arxiv.org/abs/2602.18689 SCA [7] SOK: A Taxonomy of Attack Vectors and Defense Strategies for Agentic Supply Chain Runtime arXiv · Research · https://arxiv.org/abs/2602.19555 [8] On the Variability of Source Code in Maven Package Rebuilds arXiv · Research · https://arxiv.org/abs/2602.19383 [9] 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 [10] Package Managers à la Carte: A Formal Model of Dependency Resolution arXiv · Research · https://arxiv.org/abs/2602.18602 DAST [11] ICSSPulse: A Modular LLM-Assisted Platform for Industrial Control System Penetration Testing arXiv · Research · https://arxiv.org/abs/2602.20663 [12] FuzzySQL: Uncovering Hidden Vulnerabilities in DBMS Special Features with LLM-Driven Fuzzing arXiv · Research · https://arxiv.org/abs/2602.19490 [13] Can AI Lower the Barrier to Cybersecurity? A Human-Centered Mixed-Methods Study of Novice CTF Learning arXiv · Research · https://arxiv.org/abs/2602.18172 [14] What Makes a Good LLM Agent for Real-world Penetration Testing? arXiv · Research · https://arxiv.org/abs/2602.17622 AGENTIC SDLC [15] AdapTools: Adaptive Tool-based Indirect Prompt Injection Attacks on Agentic LLMs arXiv · Research · https://arxiv.org/abs/2602.20720 [16] When AI Teammates Meet Code Review: Collaboration Signals Shaping the Integration of Agent-Authored Pull Requests arXiv · Research · https://arxiv.org/abs/2602.19441 [17] GraphSkill: Documentation-Guided Hierarchical Retrieval-Augmented Coding for Complex Graph Reasoning arXiv · Research · https://arxiv.org/abs/2603.06620 [18] Can Adversarial Code Comments Fool AI Security Reviewers -- Large-Scale Empirical Study of Comment-Based Attacks and Defenses Against LLM Code Analysis arXiv · Research · https://arxiv.org/abs/2602.16741 REMEDIATION [19] Red-Teaming Claude Opus and ChatGPT-based Security Advisors for Trusted Execution Environments arXiv · Research · https://arxiv.org/abs/2602.19450 [20] Microsoft Patches CVE-2026-26119 Privilege Escalation in Windows Admin Center The Hacker News · Analysis · https://thehackernews.com/2026/02/microsoft-patches-cve-2026-26119.html [21] AI Found Twelve New Vulnerabilities in OpenSSL Schneier on Security · Analysis · https://schneier.com/blog/archives/2026/02/ai-found-twelve-new-vulnerabilities-in-openssl.html [22] Anthropic Launches Claude Code Security for AI-Powered Vulnerability Scanning The Hacker News · Announcement · https://thehackernews.com/2026/02/anthropic-launches-claude-code-security.html TRUST [23] 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 [24] Right to History: A Sovereignty Kernel for Verifiable AI Agent Execution arXiv · Research · https://arxiv.org/abs/2602.20214 [25] OpenPort Protocol: A Security Governance Specification for AI Agent Tool Access arXiv · Research · https://arxiv.org/abs/2602.20196 [26] From Docs to Descriptions: Smell-Aware Evaluation of MCP Server Descriptions arXiv · Research · https://arxiv.org/abs/2602.18914 MODELS [27] CREDIT: Certified Ownership Verification of Deep Neural Networks Against Model Extraction Attacks arXiv · Research · https://arxiv.org/abs/2602.20419 [28] CITED: A Decision Boundary-Aware Signature for GNNs Towards Model Extraction Defense arXiv · Research · https://arxiv.org/abs/2602.20418 [29] CIBER: A Comprehensive Benchmark for Security Evaluation of Code Interpreter Agents arXiv · Research · https://arxiv.org/abs/2602.19547 [30] When Backdoors Go Beyond Triggers: Semantic Drift in Diffusion Models Under Encoder Attacks arXiv · Research · https://arxiv.org/abs/2602.20193 AI SECURITY [31] ICON: Indirect Prompt Injection Defense for Agents based on Inference-Time Correction arXiv · Research · https://arxiv.org/abs/2602.20708 [32] Skill-Inject: Measuring Agent Vulnerability to Skill File Attacks arXiv · Research · https://arxiv.org/abs/2602.20156 [33] The LLMbda Calculus: AI Agents, Conversations, and Information Flow arXiv · Research · https://arxiv.org/abs/2602.20064 [34] Security Risks of AI Agents Hiring Humans: An Empirical Marketplace Study arXiv · Research · https://arxiv.org/abs/2602.19514 ADVISORIES IN THIS WINDOW 138 npm advisories · 34 critical · 56 high · 39 moderate · 9 low 29 PyPI advisories · 4 critical · 11 high · 10 moderate · 4 low 23 Go advisories · 2 critical · 7 high · 10 moderate · 4 low 22 Packagist advisories · 1 critical · 7 high · 11 moderate · 3 low 11 Maven advisories · 2 critical · 4 high · 2 moderate · 3 low 6 crates.io advisories · 4 high · 1 moderate · 1 low 2 RubyGems advisories · 1 high · 1 moderate 1 Swift advisory · 1 moderate 1 GitHub Actions advisory · 1 moderate 1 Multi-ecosystem 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.