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, Friday 31 July 2026 Retrospective Covers 30 July 2026 00:00 to 31 July 2026 00:00 UTC Web: https://keryn.dev/headlines/daily/2026-07-31/ TOP DEVELOPMENTS [1] Microsoft Teams vishing attacks lead to Chaos ransomware attacks BleepingComputer · Incident · https://bleepingcomputer.com/news/security/microsoft-teams-vishing-attacks-lead-to-chaos-ransomware-attacks [2] CosmosEscape: Taking Over Every Database in Azure Cosmos DB Wiz · Analysis · https://wiz.io/blog/cosmosescape-taking-over-every-database-in-azure-cosmos-db [3] Hackers Exploit AnySign4PC via Hacked Korean Sites to Install Backdoors Without Prompts The Hacker News · Incident · https://thehackernews.com/2026/07/hackers-exploit-anysign4pc-via-hacked.html SCA [4] Emerging Challenges in Threat Modeling for GenAI-Augmented Systems: A View from the Trenches arXiv · Research · https://arxiv.org/abs/2607.28431 [5] Security of World-Model-Based Embodied AI: A Lifecycle of Threats, Defenses, and Evaluation arXiv · Research · https://arxiv.org/abs/2607.28226 [6] Don't Trust the AI Ecosystem: Analyzing Privacy Leakage in Compromised Open-Source Components arXiv · Research · https://arxiv.org/abs/2607.27886 AGENTIC SDLC [7] Change2Task: From Repository Changes to Executable Coding Agent Tasks and Environments arXiv · Research · https://arxiv.org/abs/2607.28591 [8] Escaping Linux Sandboxes via PipeWire (CVE-2026-5674) Embrace The Red · Analysis · https://embracethered.com/blog/posts/2026/pipewire-flatpak-linux-sandbox-escape-cve-2026-5674 [9] Secure at Inception: Announcing the Snyk Studio Integration for Snowflake Cortex Code Snyk · Analysis · https://snyk.io/blog/announcing-snyk-studio-integration-snowflake-cortex-code REMEDIATION [10] Validation Evidence in LLM Repair Agents: How Much of What Passes Actually Tests the Bug? arXiv · Research · https://arxiv.org/abs/2607.28871 [11] Google says AI helped Chrome fix 1,072 security bugs in two releases BleepingComputer · Analysis · https://bleepingcomputer.com/news/google/google-says-ai-helped-chrome-fix-1-072-security-bugs-in-two-releases [12] Russian Hackers Exploit Microsoft OWA Flaw to Keep Mailbox Access After Credential Rotation The Hacker News · Analysis · https://thehackernews.com/2026/07/russian-hackers-exploit-microsoft-owa.html MODELS [13] Temporal Poisoning: Clean-Label Backdoors via Event Redistribution in SNNs arXiv · Research · https://arxiv.org/abs/2607.28075 [14] TriShield: Zero-Utility-Loss Defense Against Privacy Backdoors in Federated Language Model Fine-Tuning via Orthogonal Gradient Projection and Optimizer State Entanglement arXiv · Research · https://arxiv.org/abs/2607.27940 [15] Benign on Label, Malicious by Design: Clean-Label Dormant-to-Activated Backdoor via Machine Unlearning with Removable Camouflage arXiv · Research · https://arxiv.org/abs/2607.27936 AI SECURITY [16] CyberNeuro: A Privacy-Preserving Agentic Workbench for Cohort-Scale Neuroimage and Clinical Data Analysis arXiv · Research · https://arxiv.org/abs/2607.28841 [17] Piggybacking on Perception: Stealthy Concurrent Audio Prompt Injections against Multimodal LLM Agents arXiv · Research · https://arxiv.org/abs/2607.28165 [18] ChemMat-AgentSafetyBench: Evaluating Long-Horizon Attacks and Defenses in Chemistry and Materials Agents arXiv · Research · https://arxiv.org/abs/2609.11952 ADVISORIES IN THIS WINDOW 212 npm advisories · 211 critical · 1 high 10 PyPI advisories · 5 critical · 4 high · 1 moderate 7 RubyGems advisories · 1 critical · 2 high · 3 moderate · 1 low 3 Go advisories · 1 high · 2 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.