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 16 of 2026 Retrospective Covers 7 April 2026 11:00 to 14 April 2026 11:00 UTC Web: https://keryn.dev/headlines/weekly/2026-W16/ TOP DEVELOPMENTS [1] CVE-2026-34621: Adobe Acrobat and Reader Prototype Pollution Vulnerability added to CISA's Known Exploited Vulnerabilities catalog CISA · Advisory · https://cisa.gov/known-exploited-vulnerabilities-catalog?search_api_fulltext=CVE-2026-34621 [2] Anthropic's Project Glasswing - restricting Claude Mythos to security researchers - sounds necessary to me Simon Willison · Research · https://simonwillison.net/2026/Apr/7/project-glasswing [3] CVE-2020-9715: Adobe Acrobat Use-After-Free Vulnerability added to CISA's Known Exploited Vulnerabilities catalog CISA · Advisory · https://cisa.gov/known-exploited-vulnerabilities-catalog?search_api_fulltext=CVE-2020-9715 [4] Analysis of one billion CISA KEV remediation records exposes limits of human-scale security BleepingComputer · Research · https://bleepingcomputer.com/news/security/analysis-of-one-billion-cisa-kev-remediation-records-exposes-limits-of-human-scale-security [5] OpenAI rotates macOS certs after Axios attack hit code-signing workflow BleepingComputer · Analysis · https://bleepingcomputer.com/news/security/openai-rotates-macos-certs-after-axios-attack-hit-code-signing-workflow SAST [6] Verify Before You Fix: Agentic Execution Grounding for Trustworthy Cross-Language Code Analysis arXiv · Research · https://arxiv.org/abs/2604.10800 [7] The Code Whisperer: LLM and Graph-Based AI for Smell and Vulnerability Resolution arXiv · Research · https://arxiv.org/abs/2604.13114 [8] VulWeaver: Weaving Broken Semantics for Grounded Vulnerability Detection arXiv · Research · https://arxiv.org/abs/2604.10767 [9] VCAO: Verifier-Centered Agentic Orchestration for Strategic OS Vulnerability Discovery arXiv · Research · https://arxiv.org/abs/2604.08291 SCA [10] Behind the Scenes: How StepSecurity Detected and Helped Remediate the Largest npm Supply Chain Attack StepSecurity · Incident · https://stepsecurity.io/blog/behind-the-scenes-how-stepsecurity-detected-and-helped-remediate-the-largest-npm-supply-chain-attack [11] @velora-dex/sdk Compromised on npm: Malicious Version Drops macOS Backdoor via launchctl Persistence StepSecurity · Incident · https://stepsecurity.io/blog/velora-dex-sdk-compromised-on-npm-malicious-version-drops-macos-backdoor-via-launchctl-persistence [12] Our response to the Axios developer tool compromise OpenAI News · Incident · https://openai.com/index/axios-developer-tool-compromise [13] Security and Resilience in Autonomous Vehicles: A Proactive Design Approach arXiv · Research · https://arxiv.org/abs/2604.12408 DAST [14] Why Your Automated Pentesting Tool Just Hit a Wall BleepingComputer · Analysis · https://bleepingcomputer.com/news/security/why-your-automated-pentesting-tool-just-hit-a-wall [15] Hackers or Hallucinators? A Comprehensive Analysis of LLM-Based Automated Penetration Testing arXiv · Research · https://arxiv.org/abs/2604.05719 AGENTIC SDLC [16] LLM-Redactor: An Empirical Evaluation of Eight Techniques for Privacy-Preserving LLM Requests arXiv · Research · https://arxiv.org/abs/2604.12064 [17] Resilient Write: A Six-Layer Durable Write Surface for LLM Coding Agents arXiv · Research · https://arxiv.org/abs/2604.10842 [18] Securing Vibe Coding and AI Coding Agents: An End-to-End Approach with StepSecurity StepSecurity · Analysis · https://stepsecurity.io/blog/securing-vibe-coding-and-ai-coding-agents-an-end-to-end-approach-with-stepsecurity [19] Security Concerns in Generative AI Coding Assistants: Insights from Online Discussions on GitHub Copilot arXiv · Research · https://arxiv.org/abs/2604.08352 REMEDIATION [20] Intent redirection vulnerability in third-party SDK exposed millions of Android wallets to potential risk Microsoft · Research · https://microsoft.com/en-us/security/blog/2026/04/09/intent-redirection-vulnerability-third-party-sdk-android [21] A Queueing-Theoretic Framework for Dynamic Attack Surfaces: Data-Integrated Risk Analysis and Adaptive Defense arXiv · Research · https://arxiv.org/abs/2604.10427 [22] Fine-grained Approaches for Confidence Calibration of LLMs in Automated Code Revision arXiv · Research · https://arxiv.org/abs/2604.06723 [23] Does Pass Rate Tell the Whole Story? Evaluating Design Constraint Compliance in LLM-based Issue Resolution arXiv · Research · https://arxiv.org/abs/2604.05955 TRUST [24] Beyond Static Sandboxing: Learned Capability Governance for Autonomous AI Agents arXiv · Research · https://arxiv.org/abs/2604.11839 [25] Post-Deployment Accountability in AI Governance: A Cross-Regulatory Empirical Analysis of AI Incidents arXiv · Research · https://arxiv.org/abs/2605.16281 [26] Expanding the MCP Maintainer Team Model Context Protocol · Analysis · https://blog.modelcontextprotocol.io/posts/2026-04-08-maintainer-update [27] Blockchain and AI: Securing Intelligent Networks for the Future arXiv · Research · https://arxiv.org/abs/2604.06323 MODELS [28] DeepSeek Robustness Against Semantic-Character Dual-Space Mutated Prompt Injection arXiv · Research · https://arxiv.org/abs/2604.12548 [29] Safety Training Modulates Harmful Misalignment Under On-Policy RL, But Direction Depends on Environment Design arXiv · Research · https://arxiv.org/abs/2604.12500 [30] Scaling Exposes the Trigger: Input-Level Backdoor Detection in Text-to-Image Diffusion Models via Cross-Attention Scaling arXiv · Research · https://arxiv.org/abs/2604.12446 [31] Compiling Activation Steering into Weights via Null-Space Constraints for Stealthy Backdoors arXiv · Research · https://arxiv.org/abs/2604.12359 AI SECURITY [32] ‘GrafanaGhost’ bypasses Grafana’s AI defenses without leaving a trace CyberScoop · Research · https://cyberscoop.com/grafanaghost-grafana-prompt-injection-vulnerability-data-exfiltration [33] WebAgentGuard: A Reasoning-Driven Guard Model for Detecting Prompt Injection Attacks in Web Agents arXiv · Research · https://arxiv.org/abs/2604.12284 [34] TEMPLATEFUZZ: Fine-Grained Chat Template Fuzzing for Jailbreaking and Red Teaming LLMs arXiv · Research · https://arxiv.org/abs/2604.12232 [35] Modality-Native Routing in Agent-to-Agent Networks: A Multimodal A2A Protocol Extension arXiv · Research · https://arxiv.org/abs/2604.12213 ADVISORIES IN THIS WINDOW 203 npm advisories · 107 critical · 24 high · 62 moderate · 10 low 89 PyPI advisories · 16 critical · 27 high · 41 moderate · 5 low 76 Go advisories · 9 critical · 29 high · 33 moderate · 5 low 43 Maven advisories · 3 critical · 19 high · 19 moderate · 2 low 23 Packagist advisories · 7 high · 10 moderate · 6 low 19 crates.io advisories · 3 critical · 3 high · 9 moderate · 4 low 10 NuGet advisories · 4 high · 6 moderate 6 RubyGems advisories · 2 critical · 3 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.