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 2 of 2026 Retrospective Covers 30 December 2025 12:00 to 6 January 2026 12:00 UTC Web: https://keryn.dev/headlines/weekly/2026-W02/ TOP DEVELOPMENTS [1] CISA orders feds to patch MongoBleed flaw exploited in attacks BleepingComputer · Advisory · https://bleepingcomputer.com/news/security/cisa-orders-federal-agencies-to-patch-mongobleed-flaw-actively-exploited-in-attacks [2] Zoom Stealer browser extensions harvest corporate meeting intelligence BleepingComputer · Research · https://bleepingcomputer.com/news/security/zoom-stealer-browser-extensions-harvest-corporate-meeting-intelligence [3] AI Model Confusion: An LLM/AI Model Supply Chain Attack Checkmarx · Incident · https://checkmarx.com/zero-post/hugs-from-strangers-ai-model-confusion-supply-chain-attack [4] Researchers Spot Modified Shai-Hulud Worm Testing Payload on npm Registry The Hacker News · Incident · https://thehackernews.com/2025/12/researchers-spot-modified-shai-hulud.html [5] Critical AdonisJS Bodyparser Flaw (CVSS 9.2) Enables Arbitrary File Write on Servers The Hacker News · Advisory · https://thehackernews.com/2026/01/critical-adonisjs-bodyparser-flaw-cvss.html SAST [6] SastBench: A Benchmark for Testing Agentic SAST Triage arXiv · Research · https://arxiv.org/abs/2601.02941 [7] Focus on What Matters: Fisher-Guided Adaptive Multimodal Fusion for Vulnerability Detection arXiv · Research · https://arxiv.org/abs/2601.02438 [8] Exposing Hidden Interfaces: LLM-Guided Type Inference for Reverse Engineering macOS Private Frameworks arXiv · Research · https://arxiv.org/abs/2601.01673 [9] Improving LLM-Assisted Secure Code Generation through Retrieval-Augmented-Generation and Multi-Tool Feedback arXiv · Research · https://arxiv.org/abs/2601.00509 SCA [10] Automated SBOM-Driven Vulnerability Triage for IoT Firmware: A Lightweight Pipeline for Risk Prioritization arXiv · Research · https://arxiv.org/abs/2601.01308 [11] MCP-SandboxScan: WASM-based Secure Execution and Runtime Analysis for MCP Tools arXiv · Research · https://arxiv.org/abs/2601.01241 [12] Towards a Benchmark for Dependency Decision-Making arXiv · Research · https://arxiv.org/abs/2601.00205 [13] Supply chains, AI, and the cloud: The biggest failures (and one success) of 2025 Ars Technica: Security · Analysis · https://arstechnica.com/security/2025/12/supply-chains-ai-and-the-cloud-the-biggest-failures-and-one-success-of-2025 DAST [14] dataRLsec: Safety, Security, and Reliability With Robust Offline Reinforcement Learning for DPAs arXiv · Research · https://arxiv.org/abs/2601.01289 [15] CuFuzz: Hardening CUDA Programs through Transformation and Fuzzing arXiv · Research · https://arxiv.org/abs/2601.01048 AGENTIC SDLC [16] Are Copilot prompt injection flaws vulnerabilities or AI limits? BleepingComputer · Analysis · https://bleepingcomputer.com/news/security/are-copilot-prompt-injection-flaws-vulnerabilities-or-ai-limits [17] VSCode IDE forks expose users to "recommended extension" attacks BleepingComputer · Analysis · https://bleepingcomputer.com/news/security/vscode-ide-forks-expose-users-to-recommended-extension-attacks [18] Security in the Age of AI Teammates: An Empirical Study of Agentic Pull Requests on GitHub arXiv · Research · https://arxiv.org/abs/2601.00477 [19] Agentic ProbLLMs: Exploiting AI Computer-Use And Coding Agents (39C3 Video + Slides) Embrace The Red · Analysis · https://embracethered.com/blog/posts/2025/39c3-agentic-probllms-exploiting-computer-use-and-coding-agents REMEDIATION [20] IBM warns of critical API Connect auth bypass vulnerability BleepingComputer · Analysis · https://bleepingcomputer.com/news/security/ibm-warns-of-critical-api-connect-auth-bypass-vulnerability [21] Advanced Vulnerability Scanning for Open Source Software: Detection and Mitigation of Log4j Vulnerabilities arXiv · Research · https://arxiv.org/abs/2601.00235 [22] DynaFix: Iterative Automated Program Repair Driven by Execution-Level Dynamic Information arXiv · Research · https://arxiv.org/abs/2512.24635 TRUST [23] Interoperability in AI Safety Governance: Ethics, Regulations, and Standards arXiv · Research · https://arxiv.org/abs/2601.06153 [24] Enterprise Identity Integration for AI-Assisted Developer Services: Architecture, Implementation, and Case Study arXiv · Research · https://arxiv.org/abs/2601.02698 MODELS [25] Adversarial Contrastive Learning for LLM Quantization Attacks arXiv · Research · https://arxiv.org/abs/2601.02680 [26] TRYLOCK: Defense-in-Depth Against LLM Jailbreaks via Layered Preference and Representation Engineering arXiv · Research · https://arxiv.org/abs/2601.03300 [27] Extracting books from production language models arXiv · Research · https://arxiv.org/abs/2601.02671 [28] Hidden State Poisoning Attacks against Mamba-based Language Models arXiv · Research · https://arxiv.org/abs/2601.01972 AI SECURITY [29] Language Model Agents Under Attack: A Cross Model-Benchmark of Profit-Seeking Behaviors in Customer Service arXiv · Research · https://arxiv.org/abs/2512.24415 [30] Agentic AI Is an Identity Problem and CISOs Will Be Accountable for the Outcome BleepingComputer · Analysis · https://bleepingcomputer.com/news/security/agentic-ai-is-an-identity-problem-and-cisos-will-be-accountable-for-the-outcome [31] Structural Representations for Cross-Attack Generalization in AI Agent Threat Detection arXiv · Research · https://arxiv.org/abs/2601.01723 [32] OpenAI says prompt injection may never be ‘solved’ for browser agents like Atlas CyberScoop · Analysis · https://cyberscoop.com/openai-chatgpt-atlas-prompt-injection-browser-agent-security-update-head-of-preparedness ADVISORIES IN THIS WINDOW 106 npm advisories · 91 critical · 8 high · 7 moderate 17 Packagist advisories · 11 high · 4 moderate · 2 low 16 PyPI advisories · 6 high · 5 moderate · 5 low 7 Go advisories · 1 critical · 1 high · 4 moderate · 1 low 6 Maven advisories · 3 high · 3 moderate 3 crates.io advisories · 1 critical · 1 high · 1 moderate 2 Multi-ecosystem advisories · 2 moderate 2 NuGet advisories · 2 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.