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 16 June 2026 Retrospective Covers 15 June 2026 00:00 to 16 June 2026 00:00 UTC Web: https://keryn.dev/headlines/daily/2026-06-16/ TOP DEVELOPMENTS [1] Cisco fixes SD-WAN vManage flaw exploited in zero-day attacks BleepingComputer · Incident · https://bleepingcomputer.com/news/security/cisco-fixes-sd-wan-vmanage-flaw-exploited-in-zero-day-attacks [2] OptinMonster WordPress plugin hacked in CDN supply-chain attack BleepingComputer · Incident · https://bleepingcomputer.com/news/security/optinmonster-wordpress-plugin-hacked-in-cdn-supply-chain-attack [3] New attack turned Microsoft 365 Copilot into 1-click data theft tool BleepingComputer · Analysis · https://bleepingcomputer.com/news/security/new-attack-turned-microsoft-365-copilot-into-1-click-data-theft-tool [4] ChainVeil: A Malicious npm Supply Chain Attack by SuccessKey Checkmarx · Incident · https://checkmarx.com/zero-post/chainveil-a-malicious-npm-supply-chain-attack-by-successkey SCA [5] The Proxy Knows Too Much: Sealing LLM API Routers with Attested TEEs arXiv · Research · https://arxiv.org/abs/2606.16358 DAST [6] ARVO: Atlas of Reproducible Vulnerabilities for Open-Source Software arXiv · Research · https://arxiv.org/abs/2606.17283 AGENTIC SDLC [7] Transferable Self-Evolving Playbooks for Agentic Security Auditing arXiv · Research · https://arxiv.org/abs/2606.16420 [8] Dynamic Malicious Skills in Agentic AI arXiv · Research · https://arxiv.org/abs/2606.16287 [9] Checkmarx Security, Delivered Through Every AI Tool Your Team Already Uses Checkmarx · Analysis · https://checkmarx.com/blog/checkmarx-security-delivered-through-every-ai-tool-your-team-already-uses MODELS [10] Your Privacy My Cloak: Backdoor Attacks on Differentially Private Federated Learning arXiv · Research · https://arxiv.org/abs/2606.17035 [11] Automated jailbreak attack targeting multiple defense strategies arXiv · Research · https://arxiv.org/abs/2606.16751 [12] DoubtProbe: Black-Box Jailbreak Defense via Structural Verification and Semantic Auditing arXiv · Research · https://arxiv.org/abs/2606.16527 AI SECURITY [13] An Evaluation of Data Leakage Risks in Tool-Using LLM Agents in Realistic Scenarios arXiv · Research · https://arxiv.org/abs/2606.17114 [14] Rapid Poison: Practical Poisoning Attacks Against the Rapid Response Framework arXiv · Research · https://arxiv.org/abs/2606.16242 [15] As AI agents become employees, NewCore emerges with $66M to give them identities TechCrunch: Security · Analysis · https://techcrunch.com/2026/06/15/ai-agents-are-becoming-employees-newcore-emerges-with-66m-to-give-them-identities ADVISORIES IN THIS WINDOW 78 npm advisories · 36 critical · 17 high · 19 moderate · 6 low 25 PyPI advisories · 7 high · 9 moderate · 9 low 11 Packagist advisories · 2 critical · 2 high · 6 moderate · 1 low 9 Maven advisories · 1 critical · 5 high · 3 moderate 3 Go advisories · 3 high 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.