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, Wednesday 7 October 2026 Retrospective Covers 6 October 2026 00:00 to 7 October 2026 00:00 UTC Web: https://keryn.dev/headlines/daily/2026-10-07/ TOP DEVELOPMENTS [1] Welcome to the Jungle: What We Found Inside 15,465 Public MCP Servers The Hacker News · Research · https://thehackernews.com/2026/10/welcome-to-jungle-what-we-found-inside.html [2] Ninja Forms plugin flaw exploited to hack WordPress sites BleepingComputer · Incident · https://bleepingcomputer.com/news/security/ninja-forms-plugin-flaw-exploited-to-hack-wordpress-sites [3] You Won’t Hear About These, Even In Myths (Atlassian Jira, Confluence (and more) Pre-Auth Arbitrary File Read CVE-2026-21589) watchTowr · Analysis · https://labs.watchtowr.com/you-wont-hear-about-these-even-in-myths-atlassian-jira-confluence-and-more-pre-auth-arbitrary-file-read-cve-2026-21589 SAST [4] Learning from Failures: A Failure-Driven Prompt Refinement for LLM-Based Vulnerability Analysis arXiv · Research · https://arxiv.org/abs/2610.08405 [5] CheckerBench: Can Long-Horizon Agents Synthesize Static-Analysis Checkers? arXiv · Research · https://arxiv.org/abs/2610.07557 SCA [6] Large-scale Repository Engineering via Agent-Native Reusable Code Primitives arXiv · Research · https://arxiv.org/abs/2610.09079 AGENTIC SDLC [7] SpecGuard: Proving a Task Is Broken Before the Agent Cheats arXiv · Research · https://arxiv.org/abs/2610.09159 [8] A Case Study in Assuring AI-Written Software arXiv · Research · https://arxiv.org/abs/2610.08651 [9] HarnessSecurity-Bench: Do Security Mechanisms Really Protect Coding Agent Harnesses? arXiv · Research · https://arxiv.org/abs/2610.07639 REMEDIATION [10] CISO perspectives on managing vulnerability risks in the age of AI Microsoft · Analysis · https://microsoft.com/en-us/security/blog/2026/10/06/ciso-perspectives-on-managing-vulnerability-risks-in-the-age-of-ai [11] Aikido Security achieves FedRAMP Moderate authorization Aikido Security · Analysis · https://aikido.dev/blog/aikido-fedramp-moderate-authorization TRUST [12] OpenSSF Shares Expanded Membership and New Global Policy Resources During Community Day Europe OpenSSF · Standard / policy · https://openssf.org/press-release/2026/10/06/openssf-shares-expanded-membership-and-new-global-policy-resources-during-community-day-europe [13] TwinGuard-Lite: A Rule-Based State-Admission Gateway for Generative Patient Digital Twins arXiv · Research · https://arxiv.org/abs/2610.09012 [14] Toward Alignment Scaling Laws: A Framework and First Preregistered Measurements arXiv · Research · https://arxiv.org/abs/2610.08540 MODELS [15] Visual Memory Attacks Can Persist Through The KV Cache arXiv · Research · https://arxiv.org/abs/2610.09027 [16] Secure Speculative Decoding for Large Language Models arXiv · Research · https://arxiv.org/abs/2610.08678 [17] ProximalFM: Amortized Proximal Causal Inference under Hidden Confounding arXiv · Research · https://arxiv.org/abs/2610.08078 AI SECURITY [18] ASPIRE: Agentic Safety & Prompt Injection Red-teaming Engine arXiv · Research · https://arxiv.org/abs/2610.08951 [19] AdvSim2Real : Training Web Agents Against Adaptive Prompt Injection in a Web World Model arXiv · Research · https://arxiv.org/abs/2610.08773 [20] Surviving the Router: Optimizing Skill Injections for Retrieval and Execution arXiv · Research · https://arxiv.org/abs/2610.08098 ADVISORIES IN THIS WINDOW 33 npm advisories · 15 critical · 10 high · 6 moderate · 2 low 9 PyPI advisories · 2 critical · 1 high · 6 moderate 4 Go advisories · 2 high · 2 moderate 3 NuGet advisories · 1 critical · 1 high · 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.