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 25 of 2025 Retrospective Covers 10 June 2025 11:00 to 17 June 2025 11:00 UTC Web: https://keryn.dev/headlines/weekly/2025-W25/ TOP DEVELOPMENTS [1] Microsoft June 2025 Patch Tuesday fixes exploited zero-day, 66 flaws BleepingComputer · Advisory · https://bleepingcomputer.com/news/microsoft/microsoft-june-2025-patch-tuesday-fixes-exploited-zero-day-66-flaws [2] Zero-click AI data leak flaw uncovered in Microsoft 365 Copilot BleepingComputer · Incident · https://bleepingcomputer.com/news/security/zero-click-ai-data-leak-flaw-uncovered-in-microsoft-365-copilot [3] Fog ransomware attack uses unusual mix of legitimate and open-source tools BleepingComputer · Incident · https://bleepingcomputer.com/news/security/fog-ransomware-attack-uses-unusual-mix-of-legitimate-and-open-source-tools [4] Password-spraying attacks target 80,000 Microsoft Entra ID accounts BleepingComputer · Analysis · https://bleepingcomputer.com/news/security/password-spraying-attacks-target-80-000-microsoft-entra-id-accounts [5] An Introduction to Google’s Approach to AI Agent Security Simon Willison · Research · https://simonwillison.net/2025/Jun/15/ai-agent-security SAST [6] Identifying Helpful Context for LLM-based Vulnerability Repair: A Preliminary Study arXiv · Research · https://arxiv.org/abs/2506.11561 [7] AI-Based Software Vulnerability Detection: A Systematic Literature Review arXiv · Research · https://arxiv.org/abs/2506.10280 [8] Expert-in-the-Loop Systems with Cross-Domain and In-Domain Few-Shot Learning for Software Vulnerability Detection arXiv · Research · https://arxiv.org/abs/2506.10104 [9] ZTaint-Havoc: From Havoc Mode to Zero-Execution Fuzzing-Driven Taint Inference arXiv · Research · https://arxiv.org/abs/2506.08838 SCA [10] PyPI, npm, and AI Tools Exploited in Malware Surge Targeting DevOps and Cloud Environments The Hacker News · Incident · https://thehackernews.com/2025/06/malicious-pypi-package-masquerades-as.html [11] Information-theoretic Estimation of the Risk of Privacy Leaks arXiv · Research · https://arxiv.org/abs/2506.12328 [12] Scalable Software Testing in Fast Virtual Platforms: Leveraging SystemC, QEMU and Containerization arXiv · Research · https://arxiv.org/abs/2506.10624 [13] GUAC 1.0 is Now Available OpenSSF · Release · https://openssf.org/blog/2025/06/12/guac-1-0-is-now-available DAST [14] Recognition Without Mitigation: Ethical Frameworks in Autonomous Offensive-LLM Agent Research arXiv · Research · https://arxiv.org/abs/2506.08693 AGENTIC SDLC [15] Reasoning as a Resource: Optimizing Fast and Slow Thinking in Code Generation Models arXiv · Research · https://arxiv.org/abs/2506.09396 [16] Risks & Benefits of LLMs & GenAI for Platform Integrity, Healthcare Diagnostics, Financial Trust and Compliance, Cybersecurity, Privacy & AI Safety: A Comprehensive Survey, Roadmap & Implementation Blueprint arXiv · Research · https://arxiv.org/abs/2506.12088 [17] How the GitHub billing team uses the coding agent in GitHub Copilot to continuously burn down technical debt GitHub · Analysis · https://github.blog/ai-and-ml/github-copilot/how-the-github-billing-team-uses-the-coding-agent-in-github-copilot-to-continuously-burn-down-technical-debt REMEDIATION [18] Apple Zero-Click Flaw in Messages Exploited to Spy on Journalists Using Paragon Spyware The Hacker News · Incident · https://thehackernews.com/2025/06/apple-zero-click-flaw-in-messages.html [19] Dems want watchdog study of two troubled federally-funded vulnerability tracking initiatives CyberScoop · Research · https://cyberscoop.com/gao-vulnerability-management-letter-cve-nvd-bennie-thompson-zoe-lofgren [20] Found in the wild: 2 Secure Boot exploits. Microsoft is patching only 1 of them. Ars Technica: Security · Research · https://arstechnica.com/security/2025/06/unearthed-in-the-wild-2-secure-boot-exploits-microsoft-patches-only-1-of-them [21] Microsoft shares temp fix for Outlook crashes when opening emails BleepingComputer · Analysis · https://bleepingcomputer.com/news/microsoft/microsoft-shares-workaround-for-classic-outlook-crashes TRUST [22] Tech Talk Recap | CRA-Ready: How Open Source Projects Can Prepare for the EU Cyber Resilience Act OpenSSF · Standard / policy · https://openssf.org/blog/2025/06/16/cra-ready-how-open-source-projects-can-prepare-for-the-eu-cyber-resilience-act [23] Step-by-Step Reasoning Attack: Revealing 'Erased' Knowledge in Large Language Models arXiv · Research · https://arxiv.org/abs/2506.17279 [24] Data-Centric Safety and Ethical Measures for Data and AI Governance arXiv · Research · https://arxiv.org/abs/2506.10217 MODELS [25] Theoretically Unmasking Inference Attacks Against LDP-Protected Clients in Federated Vision Models arXiv · Research · https://arxiv.org/abs/2506.17292 [26] Unlearning-Enhanced Website Fingerprinting Attack: Against Backdoor Poisoning in Anonymous Networks arXiv · Research · https://arxiv.org/abs/2506.13563 [27] Thought Crime: Backdoors and Emergent Misalignment in Reasoning Models arXiv · Research · https://arxiv.org/abs/2506.13206 [28] Jailbreak Transferability Emerges from Shared Representations arXiv · Research · https://arxiv.org/abs/2506.12913 AI SECURITY [29] 100% effective Simon Willison · Analysis · https://simonwillison.net/2025/Jun/16/100-percent [30] We Should Identify and Mitigate Third-Party Safety Risks in MCP-Powered Agent Systems arXiv · Research · https://arxiv.org/abs/2506.13666 [31] The lethal trifecta for AI agents: private data, untrusted content, and external communication Simon Willison · Analysis · https://simonwillison.net/2025/Jun/16/the-lethal-trifecta [32] Shadow AI: Examples, Risks, and 8 Ways to Mitigate Them Mend.io · Research · https://mend.io/blog/shadow-ai-examples-risks-and-8-ways-to-mitigate-them ADVISORIES IN THIS WINDOW 61 npm advisories · 56 critical · 3 high · 2 moderate 28 Maven advisories · 2 critical · 17 high · 9 moderate 20 PyPI advisories · 1 critical · 3 high · 13 moderate · 3 low 20 Packagist advisories · 1 critical · 4 high · 14 moderate · 1 low 9 Go advisories · 1 critical · 2 high · 4 moderate · 2 low 2 RubyGems advisories · 1 critical · 1 high 2 crates.io advisories · 2 moderate 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.