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 Weekly, week 29 of 2026 Retrospective Covers 7 July 2026 11:00 to 14 July 2026 11:00 UTC Web: https://keryn.dev/headlines/weekly/2026-W29/ TOP DEVELOPMENTS [1] Injective SDK on npm infected with cryptocurrency wallet stealer BleepingComputer · Analysis · https://bleepingcomputer.com/news/security/injective-sdk-on-npm-infected-with-cryptocurrency-wallet-stealer [2] CISA orders feds to patch max severity ColdFusion flaw by Friday BleepingComputer · Advisory · https://bleepingcomputer.com/news/security/cisa-orders-feds-to-patch-max-severity-coldfusion-flaw-by-friday [3] Microsoft patches RoguePlanet Defender zero-day vulnerability BleepingComputer · Advisory · https://bleepingcomputer.com/news/microsoft/microsoft-patches-rogueplanet-defender-zero-day-vulnerability [4] jscrambler npm package publishes malicious preinstall binary StepSecurity · Analysis · https://stepsecurity.io/blog/jscrambler-npm-package-publishes-malicious-preinstall-binary [5] Ubiquiti warns of new max severity UniFi OS vulnerability BleepingComputer · Analysis · https://bleepingcomputer.com/news/security/ubiquiti-warns-of-new-max-severity-unifi-os-vulnerability SAST [6] Antiproof: Synthesizing Vulnerability Detectors and Proofs of Exploitability arXiv · Research · https://arxiv.org/abs/2607.12316 [7] Toward Inferring Accurate Context-free Grammars for Big Languages in a Black-box Setting arXiv · Research · https://arxiv.org/abs/2607.08959 [8] SeedSmith: LLM-Driven Seed Synthesis for Directed Fuzzing arXiv · Research · https://arxiv.org/abs/2607.08949 SCA [9] Skills That Don't Exist: A Large-Scale Study of Hallucinated Skill Recommendation in LLM Agents arXiv · Research · https://arxiv.org/abs/2607.12340 [10] Which Neurons Detect Malicious Code? A Probing Study of LLM Security Knowledge arXiv · Research · https://arxiv.org/abs/2607.10221 [11] Do These Violent Delights Have Violent Ends? Measuring the Post-Merge Fate of Agentic Code arXiv · Research · https://arxiv.org/abs/2607.09902 [12] Researcher Details WhatsApp-to-Host Attack Chain Using Three OpenClaw Flaws The Hacker News · Research · https://thehackernews.com/2026/07/researcher-details-whatsapp-to-host.html DAST [13] Baselines Before Architecture: Evaluating Coding Agents for Autonomous Penetration Testing arXiv · Research · https://arxiv.org/abs/2607.13085 [14] VEXAIoT: Autonomous IoT Vulnerability EXploitation using AI Agents arXiv · Research · https://arxiv.org/abs/2607.09653 [15] ScopeJudge: Cost-Aware Pre-Execution Gating for Offensive Security Agents arXiv · Research · https://arxiv.org/abs/2607.07774 [16] Finding and Understanding Miscompilation Bugs in the Solidity Compiler arXiv · Research · https://arxiv.org/abs/2607.07217 AGENTIC SDLC [17] 'Ghostcommit' hides prompt injection in images to fool AI agents, steal secrets BleepingComputer · Research · https://bleepingcomputer.com/news/security/ghostcommit-hides-prompt-injection-in-images-to-fool-ai-agents-steal-secrets [18] Trust but Verify? Uncovering the Security Debt of Autonomous Coding Agents arXiv · Research · https://arxiv.org/abs/2607.12428 [19] AutoTrace: From Patches to Triggers via Agentic Interprocedural Exploration arXiv · Research · https://arxiv.org/abs/2607.12058 [20] Predicting Acceptance and Review Effort in Human and Agent Pull Requests arXiv · Research · https://arxiv.org/abs/2607.12057 REMEDIATION [21] CISA orders feds to prioritize patching Langflow auth bypass flaw BleepingComputer · Analysis · https://bleepingcomputer.com/news/security/cisa-orders-feds-to-prioritize-patching-langflow-auth-bypass-flaw [22] Zimbra urges customers to patch critical web client XSS flaw BleepingComputer · Advisory · https://bleepingcomputer.com/news/security/zimbra-urges-customers-to-patch-critical-web-client-xss-flaw [23] Writer AI Flaw Could Let Agent Previews Leak Session Tokens Across Tenants The Hacker News · Incident · https://thehackernews.com/2026/07/writer-ai-flaw-could-let-agent-previews.html [24] Patch for Windows Defender 0-day could allow attackers to fill hard disk Ars Technica: Security · Analysis · https://arstechnica.com/security/2026/07/patch-for-windows-defender-0-day-could-allow-attackers-to-fill-hard-disk TRUST [25] Policy-Conditioned Constrained Decoding for Column-Level Access Control in Text-to-SQL arXiv · Research · https://arxiv.org/abs/2607.12341 [26] Cardano's Voltaire Governance: Complete Specification and Research Program arXiv · Research · https://arxiv.org/abs/2607.11601 [27] Falsifiable Release Gates for Self-Improving Systems: Standing Invariants at Scale arXiv · Research · https://arxiv.org/abs/2607.13070 [28] The Replicant in Your Directory: AI Agents and the Identity Security Gap BleepingComputer · Analysis · https://bleepingcomputer.com/news/security/the-replicant-in-your-directory-ai-agents-and-the-identity-security-gap MODELS [29] Breaking Refusal in the First Half: A Mechanistic Study of the Prefill Jailbreak arXiv · Research · https://arxiv.org/abs/2607.14147 [30] Agent-Safety Evaluations as Load-Bearing Evidence: A Vendor-Neutral, Cross-Harness Reconstructability Metric arXiv · Research · https://arxiv.org/abs/2607.12469 [31] Grok 4.5 Model Card Cursor · Analysis · https://cursor.com/blog/grok-4-5-model-card [32] Input-Aware Dynamic Backdoor Attack Against Quantum Neural Networks arXiv · Research · https://arxiv.org/abs/2607.11843 AI SECURITY [33] Isolation as a First-Class Principle for LLM-Agent System Safety: Concepts, Taxonomy, Challenges and Future Directions arXiv · Research · https://arxiv.org/abs/2607.12406 [34] Now, defenders are embracing the prompt injection, too Ars Technica: Security · Analysis · https://arstechnica.com/security/2026/07/now-defenders-are-embracing-the-prompt-injection-too [35] Mako: A Self-Evolving Agentic Operating System (SE-AOS) for Autonomous Web Exploitation arXiv · Research · https://arxiv.org/abs/2607.11288 [36] SingGuard-NSFA: Extensible Guardrails for Agentic AI via Generative Reasoning and Real-Time Classification arXiv · Research · https://arxiv.org/abs/2607.13081 ADVISORIES IN THIS WINDOW 503 npm advisories · 484 critical · 11 high · 6 moderate · 2 low 51 Go advisories · 30 critical · 7 high · 12 moderate · 2 low 49 PyPI advisories · 9 critical · 17 high · 22 moderate · 1 low 47 Packagist advisories · 7 critical · 17 high · 21 moderate · 2 low 15 Maven advisories · 2 critical · 7 high · 6 moderate 13 RubyGems advisories · 3 high · 10 moderate 9 Hex advisories · 5 high · 1 moderate · 3 low 8 crates.io advisories · 1 critical · 2 high · 4 moderate · 1 low 1 Multi-ecosystem 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.