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 Daily, Tuesday 24 February 2026 Retrospective Covers 23 February 2026 00:00 to 24 February 2026 00:00 UTC Web: https://keryn.dev/headlines/daily/2026-02-24/ 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] 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 [3] Wormable XMRig Campaign Uses BYOVD Exploit and Time-Based Logic Bomb The Hacker News · Incident · https://thehackernews.com/2026/02/wormable-xmrig-campaign-uses-byovd.html SCA [4] SOK: A Taxonomy of Attack Vectors and Defense Strategies for Agentic Supply Chain Runtime arXiv · Research · https://arxiv.org/abs/2602.19555 DAST [5] FuzzySQL: Uncovering Hidden Vulnerabilities in DBMS Special Features with LLM-Driven Fuzzing arXiv · Research · https://arxiv.org/abs/2602.19490 AGENTIC SDLC [6] When AI Teammates Meet Code Review: Collaboration Signals Shaping the Integration of Agent-Authored Pull Requests arXiv · Research · https://arxiv.org/abs/2602.19441 [7] Why Claude Code Security Is a Big Moment for Application Security Mend.io · Analysis · https://mend.io/blog/claude-code-security-vs-enterprise-appsec REMEDIATION [8] Red-Teaming Claude Opus and ChatGPT-based Security Advisors for Trusted Execution Environments arXiv · Research · https://arxiv.org/abs/2602.19450 TRUST [9] Right to History: A Sovereignty Kernel for Verifiable AI Agent Execution arXiv · Research · https://arxiv.org/abs/2602.20214 MODELS [10] CREDIT: Certified Ownership Verification of Deep Neural Networks Against Model Extraction Attacks arXiv · Research · https://arxiv.org/abs/2602.20419 [11] CITED: A Decision Boundary-Aware Signature for GNNs Towards Model Extraction Defense arXiv · Research · https://arxiv.org/abs/2602.20418 [12] CIBER: A Comprehensive Benchmark for Security Evaluation of Code Interpreter Agents arXiv · Research · https://arxiv.org/abs/2602.19547 AI SECURITY [13] Skill-Inject: Measuring Agent Vulnerability to Skill File Attacks arXiv · Research · https://arxiv.org/abs/2602.20156 [14] The LLMbda Calculus: AI Agents, Conversations, and Information Flow arXiv · Research · https://arxiv.org/abs/2602.20064 [15] Security Risks of AI Agents Hiring Humans: An Empirical Marketplace Study arXiv · Research · https://arxiv.org/abs/2602.19514 ADVISORIES IN THIS WINDOW 5 npm advisories · 3 critical · 1 high · 1 moderate 4 PyPI advisories · 1 critical · 1 high · 2 low 3 Packagist advisories · 1 high · 2 moderate 2 Go advisories · 2 high 2 Maven advisories · 1 critical · 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.