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 21 July 2026 Retrospective Covers 20 July 2026 00:00 to 21 July 2026 00:00 UTC Web: https://keryn.dev/headlines/daily/2026-07-21/ TOP DEVELOPMENTS [1] JadePuffer agentic attacks now target AI model data with ransomware BleepingComputer · Incident · https://bleepingcomputer.com/news/security/jadepuffer-agentic-attacks-now-target-ai-model-data-with-ransomware [2] Cursor, Codex, Gemini CLI, Antigravity hit by sandbox escapes BleepingComputer · Research · https://bleepingcomputer.com/news/security/cursor-codex-gemini-cli-antigravity-hit-by-sandbox-escapes [3] Hackers are exploiting recently patched WordPress bugs, putting millions of websites at risk TechCrunch: Security · Advisory · https://techcrunch.com/2026/07/20/hackers-are-exploiting-recently-patched-wordpress-bugs-putting-millions-of-websites-at-risk DAST [4] KernelDiag: Agent-Based Root Cause Diagnosis for Kernel Crashes arXiv · Research · https://arxiv.org/abs/2607.17722 AGENTIC SDLC [5] RECEIPT: Deterministic, Reward-Hacking-Resistant Verification for White-Box Agentic XSS Discovery arXiv · Research · https://arxiv.org/abs/2607.18575 [6] CORVUS: Context Optimization and Reduction Via Underlying Synchronization for LLM Coding Agents arXiv · Research · https://arxiv.org/abs/2607.22711 [7] Why blocking AI models won’t stop the cyber threats they create CyberScoop · Analysis · https://cyberscoop.com/why-blocking-ai-models-wont-stop-cyber-threats-op-ed REMEDIATION [8] Windows KB5121767 OOB update fixes shutdowns on some Dell PCs BleepingComputer · Analysis · https://bleepingcomputer.com/news/microsoft/microsoft-fixes-windows-bug-causing-some-dell-pcs-to-shut-down TRUST [9] An approach to systemic risks of AI through the lens of emergence, collective action problems, and externalities arXiv · Research · https://arxiv.org/abs/2607.18170 MODELS [10] The Chronos Vulnerability: A Taxonomy of Temporal Persistence and Memory-Based Deception in Agentic AI arXiv · Research · https://arxiv.org/abs/2607.19433 [11] LLM Safety Alignment in Low-Resource Languages: A Systematic Literature Review arXiv · Research · https://arxiv.org/abs/2608.14626 [12] JailMeter: An Evidence-Based Evaluation Framework for Jailbreak Attacks on Large Language Models arXiv · Research · https://arxiv.org/abs/2607.19424 AI SECURITY [13] ChainWatch: A Kill Chain-Aligned Sequential Detection Framework for Multi-Step Attacks in MCP-Based AI Agent Systems arXiv · Research · https://arxiv.org/abs/2607.19432 [14] Trusted Credentials, Untrusted Behavior: Benchmarking LLM-Agent Security in High-Performance Computing arXiv · Research · https://arxiv.org/abs/2607.18485 [15] Adaptive Adversaries: A Multi-Turn, Multi-LLM Benchmark for LLM Agent Security arXiv · Research · https://arxiv.org/abs/2607.18063 ADVISORIES IN THIS WINDOW 272 NuGet advisories · 263 critical · 8 high · 1 moderate 122 npm advisories · 97 critical · 9 high · 12 moderate · 4 low 29 PyPI advisories · 2 critical · 15 high · 12 moderate 8 Packagist advisories · 1 high · 7 moderate 7 Go advisories · 3 high · 3 moderate · 1 low 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.