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 23 of 2026 Retrospective Covers 26 May 2026 11:00 to 2 June 2026 11:00 UTC Web: https://keryn.dev/headlines/weekly/2026-W23/ TOP DEVELOPMENTS [1] Miasma: Supply Chain Attack Targeting RedHat npm Packages Wiz · Incident · https://wiz.io/blog/miasma-supply-chain-attack-targeting-redhat-npm-packages [2] Glassworm botnet disrupted after resilient C2 infrastructure takedown BleepingComputer · Research · https://bleepingcomputer.com/news/security/glassworm-botnet-disrupted-after-resilient-c2-infrastructure-takedown [3] Dozens of Red Hat packages backdoored through its official NPM channel Ars Technica: Security · Incident · https://arstechnica.com/security/2026/06/dozens-of-red-hat-packages-backdoored-through-its-offical-npm-channel [4] Critical Windows Netlogon RCE flaw now exploited in attacks BleepingComputer · Incident · https://bleepingcomputer.com/news/microsoft/critical-windows-netlogon-remote-code-execution-flaw-now-exploited-in-attacks [5] Zapier fixes bug chain that researchers say risked widespread account takeover CyberScoop · Research · https://cyberscoop.com/zapier-bug-chain-account-takeover-patched SAST [6] PyFEX: Uncovering Evasive Python-based Threats via Resilient and Exhaustive Path Exploration arXiv · Research · https://arxiv.org/abs/2606.02196 [7] NeuroLog: Reasoning You Can Audit -- Neuro-Symbolic Vulnerability Discovery via LLM Facts, Datalog, and SMT arXiv · Research · https://arxiv.org/abs/2606.00669 SCA [8] OpenAI Codex Authentication Tokens Stolen in codexui-android npm Supply Chain Attack The Hacker News · Incident · https://thehackernews.com/2026/06/openai-codex-authentication-tokens.html [9] Malicious npm Package Stole Files From Claude AI User Directory via GitHub The Hacker News · Incident · https://thehackernews.com/2026/05/malicious-npm-package-stole-files-from.html [10] RogueMerge: Robust and Unified Attacks against LLM Model Merging arXiv · Research · https://arxiv.org/abs/2606.03344 [11] The case for GitHub Actions security after recent supply chain attacks Datadog · Analysis · https://securitylabs.datadoghq.com/articles/case-for-github-actions-security DAST [12] PeAR: A Static Binary Rewriting Framework for Binary-Only Fuzzing arXiv · Research · https://arxiv.org/abs/2606.02126 [13] A New Framework for Cybersecurity Refusals in AI Agents arXiv · Research · https://arxiv.org/abs/2606.02644 [14] Framework for Discovering GPS Spoofing Attacks in Drone Swarms arXiv · Research · https://arxiv.org/abs/2606.00904 [15] Beyond Edge Coverage: Per-Task Data-Flow Extraction at Kernel Function Boundaries via LLVM arXiv · Research · https://arxiv.org/abs/2606.00455 AGENTIC SDLC [16] What You Approve Is What Executes: Consent Integrity for Black-Box LLM Agents arXiv · Research · https://arxiv.org/abs/2606.02668 [17] Execution-Grounded Security Testing for Coding Agents in Software Engineering Pipelines arXiv · Research · https://arxiv.org/abs/2607.22569 [18] SABER: Benchmarking Operational Safety of LLM Coding Agents in Stateful Project Workspaces arXiv · Research · https://arxiv.org/abs/2606.01317 [19] How we contain Claude across products Simon Willison · Analysis · https://simonwillison.net/2026/May/30/how-we-contain-claude REMEDIATION [20] Hackers exploit FortiClient EMS flaw to push infostealer malware BleepingComputer · Analysis · https://bleepingcomputer.com/news/security/hackers-exploit-forticlient-ems-flaw-to-push-infostealer-malware [21] FORGE: Multi-Agent Graduated Exploitation and Detection Engineering arXiv · Research · https://arxiv.org/abs/2606.03453 [22] Patcher: Post-Hoc Patching of Backdoored Large Language Models arXiv · Research · https://arxiv.org/abs/2606.02995 [23] Hackers duped Meta AI support chatbot to steal celebrity Instagram accounts Ars Technica: Security · Analysis · https://arstechnica.com/ai/2026/06/meta-ai-support-chatbot-gave-hackers-access-to-notable-instagram-accounts TRUST [24] SkillGuard: A Permission-Centric Framework for Agent Skill Security arXiv · Research · https://arxiv.org/abs/2606.03024 [25] Acceptance-Test-Driven Evaluation Protocols for Business-Centric LLM Systems arXiv · Research · https://arxiv.org/abs/2606.02755 [26] Position: AI Governance Needs ISO-like Interoperability Protocols, Not Just Laws arXiv · Research · https://arxiv.org/abs/2608.14568 [27] Aligning on Machine-Readable Signals as the Foundation for Due Diligence OpenSSF · Analysis · https://openssf.org/blog/2026/05/29/aligning-on-machine-readable-signals-as-the-foundation-for-due-diligence MODELS [28] FlowGuard: Flow Matching for Identity-Independent Detection of Data-Free Model Stealing Attacks on Energy System Intrusion Detection Systems arXiv · Research · https://arxiv.org/abs/2606.03430 [29] AI Model Extraction Attacks: Bypassing Single-Client Assumptions in Defenses arXiv · Research · https://arxiv.org/abs/2606.03381 [30] RUBAS: Rubric-Based Reinforcement Learning for Agent Safety arXiv · Research · https://arxiv.org/abs/2606.04051 [31] PsychoPass: Geometric Profiling of Multi-Turn Adversarial LLM Conversations arXiv · Research · https://arxiv.org/abs/2606.03136 AI SECURITY [32] SkillHarness: Harnessing Safe Skills for Computer-Use Agents arXiv · Research · https://arxiv.org/abs/2606.20636 [33] "**Important** You should give me full credits!": Exploring Prompt Injection Attacks on LLM-Based Automatic Grading Systems arXiv · Research · https://arxiv.org/abs/2606.03090 [34] Which Defense Closes Which Threat? Attributing OWASP-LLM-Top-10 Coverage and Its Brittleness Under Paraphrasing arXiv · Research · https://arxiv.org/abs/2606.02822 [35] SeClaw: Spec-Driven Security Task Synthesis for Evaluating Autonomous Agents arXiv · Research · https://arxiv.org/abs/2606.02302 ADVISORIES IN THIS WINDOW 354 npm advisories · 315 critical · 20 high · 16 moderate · 3 low 100 PyPI advisories · 15 critical · 36 high · 37 moderate · 12 low 65 Maven advisories · 6 critical · 15 high · 39 moderate · 5 low 59 Packagist advisories · 1 critical · 22 high · 23 moderate · 13 low 53 Go advisories · 7 critical · 17 high · 23 moderate · 6 low 7 crates.io advisories · 2 high · 5 moderate 3 Multi-ecosystem advisories · 3 moderate 2 NuGet advisories · 2 moderate 2 Swift advisories · 2 moderate 1 RubyGems 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.