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, Thursday 10 September 2026 Retrospective Covers 9 September 2026 00:00 to 10 September 2026 00:00 UTC Web: https://keryn.dev/headlines/daily/2026-09-10/ TOP DEVELOPMENTS [1] Google warns of new Chrome zero-day bug exploited in attacks BleepingComputer · Incident · https://bleepingcomputer.com/news/security/google-patches-seventh-chrome-zero-day-exploited-in-attacks-this-year [2] New Microsoft Defender 'ShieldCrash' zero-day grants SYSTEM access BleepingComputer · Research · https://bleepingcomputer.com/news/security/new-microsoft-defender-shieldcrash-zero-day-grants-system-access [3] CVE-2026-87491: Google Chromium V8 Out of Bounds Write Vulnerability added to CISA's Known Exploited Vulnerabilities catalog CISA · Advisory · https://cisa.gov/known-exploited-vulnerabilities-catalog?search_api_fulltext=CVE-2026-87491 [4] An alignment assessment of recent cybersecurity incidents Anthropic · Research · https://anthropic.com/research/alignment-assessment-cybersecurity-incidents SAST [5] Beyond Static Guarantees: Measuring the Static-Pass Dynamic-Fail Gap in Security-Sensitive and LLM-Generated Python Code arXiv · Research · https://arxiv.org/abs/2609.10762 [6] Towards Scalable and Cost-Efficient Vulnerability Detection: A Study on Automatic Query Generation arXiv · Research · https://arxiv.org/abs/2609.10412 SCA [7] npm extends recovery-code security holds to all accounts GitHub · Analysis · https://github.blog/changelog/2026-09-09-npm-extends-recovery-code-security-holds-to-all-accounts [8] SPDX Articles in Journal of Innovation SPDX · Analysis · https://spdx.dev/spdx-articles-in-journal-of-innovation [9] Webinar: Learn How to Answer “Are We Exposed?” Faster After a New CVE The Hacker News · Guide · https://thehackernews.com/2026/09/webinar-learn-how-to-answer-are-we.html DAST [10] Big Enough to Break Out: Tracking the Rising Capability of LLM Penetration-Testing Agents arXiv · Research · https://arxiv.org/abs/2609.10780 [11] The state of AI for security: Measuring what matters most for building trust AWS Security Blog · Analysis · https://aws.amazon.com/blogs/security/the-state-of-ai-for-security-measuring-what-matters-most-for-building-trust AGENTIC SDLC [12] DeepSeek Harness Flaw Let AI Agents Disable Their Own File Sandbox Without Approval The Hacker News · Analysis · https://thehackernews.com/2026/09/deepseek-harness-flaw-let-ai-agents.html REMEDIATION [13] Chrome V8 Zero-Day Exploited in the Wild Enables Code Execution Inside Sandbox The Hacker News · Incident · https://thehackernews.com/2026/09/chrome-v8-zero-day-exploited-in-wild.html [14] Microsoft Patches Record 974 Flaws, Including Two Exploited Windows Zero-Days The Hacker News · Advisory · https://thehackernews.com/2026/09/microsoft-patches-record-974-flaws.html [15] Four groups caught using the same Chrome and Windows exploit kit Ars Technica: Security · Analysis · https://arstechnica.com/information-technology/2026/09/4-groups-caught-using-the-same-chrome-and-windows-exploit-kit TRUST [16] Beyond Training: A Feasibility Taxonomy for Inference-Time AI Governance arXiv · Research · https://arxiv.org/abs/2609.10105 MODELS [17] What Makes Adversarial Examples Transfer Across Deepfake Detectors? arXiv · Research · https://arxiv.org/abs/2609.10002 [18] CS-Guard: Benchmarking LLM Guardrails for Code Generation Security arXiv · Research · https://arxiv.org/abs/2609.09798 [19] SoK: Privacy Attacks on Machine Learning via Explainable AI arXiv · Research · https://arxiv.org/abs/2609.10627 AI SECURITY [20] DriftNet: A Dual-Head Trajectory Transformer for Detecting and Localizing Prompt Injection in LLM Agents arXiv · Research · https://arxiv.org/abs/2609.10892 [21] No-Box Vulnerability Analysis: Description-only Detection of Indirect Prompt Injection Vulnerabilities in MCP Servers arXiv · Research · https://arxiv.org/abs/2609.10854 [22] Architecting the Secure AI-SOC: A Neurosymbolic Framework for Pipeline Integrity and Threat Mitigation arXiv · Research · https://arxiv.org/abs/2609.10707 ADVISORIES IN THIS WINDOW 63 npm advisories · 58 critical · 5 high 12 PyPI advisories · 4 critical · 2 high · 6 moderate 8 Go advisories · 3 high · 4 moderate · 1 low 4 NuGet advisories · 3 high · 1 moderate 1 Maven advisory · 1 high 1 RubyGems advisory · 1 moderate 1 crates.io 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.