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 18 June 2026 Retrospective Covers 17 June 2026 00:00 to 18 June 2026 00:00 UTC Web: https://keryn.dev/headlines/daily/2026-06-18/ TOP DEVELOPMENTS [1] Microsoft working on Defender patch for RoguePlanet zero-day BleepingComputer · Advisory · https://bleepingcomputer.com/news/microsoft/microsoft-working-on-defender-patch-for-rogueplanet-zero-day [2] The Red Agent POV: How it Reasoned its Way to SSRF Wiz · Research · https://wiz.io/blog/red-agent-pov-ssrf [3] Cybercriminals allegedly hacked tens of thousands of Fortinet firewalls used by major companies all over the world TechCrunch: Security · Incident · https://techcrunch.com/2026/06/17/cybercriminals-allegedly-hacked-tens-of-thousands-of-fortinet-firewalls-used-by-major-companies-all-over-the-world SAST [4] Beyond the benchmark: Advancing security at AI speed Microsoft · Analysis · https://microsoft.com/en-us/security/blog/2026/06/17/beyond-the-benchmark-advancing-security-at-ai-speed [5] OpenAnt: LLM-Powered Vulnerability Discovery Through Code Decomposition, Adversarial Verification, and Dynamic Testing arXiv · Research · https://arxiv.org/abs/2606.19149 [6] PYPILINE: Malicious PyPI Package Detection via Suspicious API Knowledge and Agent Workflow arXiv · Research · https://arxiv.org/abs/2606.19063 SCA [7] PhantomSkill: Malicious Code Injection in Agent Skill Ecosystems arXiv · Research · https://arxiv.org/abs/2606.19191 AGENTIC SDLC [8] SWE-Future: Forecast-Conditioned Data Synthesis for Future-Oriented Software Engineering Agents arXiv · Research · https://arxiv.org/abs/2606.18733 [9] Getting more from each token: How Copilot improves context handling and model routing GitHub · Analysis · https://github.blog/ai-and-ml/github-copilot/getting-more-from-each-token-how-copilot-improves-context-handling-and-model-routing MODELS [10] FloatDoor: Platform-Triggered Backdoors in LLMs arXiv · Research · https://arxiv.org/abs/2606.19535 [11] CAPRA: Scaling Feedback on Software Architecture Deliverables with a Multi-Agent LLM System arXiv · Research · https://arxiv.org/abs/2606.18976 [12] Stealthy World Model Manipulation via Data Poisoning arXiv · Research · https://arxiv.org/abs/2606.18697 AI SECURITY [13] A Layered Security Framework Against Prompt Injection in RAG-Based Chatbots arXiv · Research · https://arxiv.org/abs/2606.19660 [14] Amplify, Don't Create: Temporal Accumulation for Slow-Burn Prompt Injection arXiv · Research · https://arxiv.org/abs/2606.20746 [15] Analyzing the Narration Gap in LLM-Solver Loops arXiv · Research · https://arxiv.org/abs/2606.19588 ADVISORIES IN THIS WINDOW 115 npm advisories · 100 critical · 3 high · 11 moderate · 1 low 21 PyPI advisories · 2 critical · 9 high · 10 moderate 9 Maven advisories · 3 critical · 3 high · 3 moderate 6 Go advisories · 3 high · 3 moderate 5 Packagist advisories · 3 high · 2 moderate 2 RubyGems advisories · 1 critical · 1 moderate 1 crates.io advisory · 1 moderate 1 Hex 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.