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 1 of 2026 Retrospective Covers 23 December 2025 12:00 to 30 December 2025 12:00 UTC Web: https://keryn.dev/headlines/weekly/2026-W01/ TOP DEVELOPMENTS [1] Strengthening supply chain security: Preparing for the next malware campaign GitHub · Incident · https://github.blog/security/supply-chain-security/strengthening-supply-chain-security-preparing-for-the-next-malware-campaign [2] 27 Malicious npm Packages Used as Phishing Infrastructure to Steal Login Credentials The Hacker News · Research · https://thehackernews.com/2025/12/27-malicious-npm-packages-used-as.html [3] MongoBleed (CVE-2025-14847) exploited in the wild: everything you need to know Wiz · Incident · https://wiz.io/blog/mongobleed-cve-2025-14847-exploited-in-the-wild-mongodb SCA [4] Trust Wallet says 2,596 wallets drained in $7 million crypto theft attack BleepingComputer · Analysis · https://bleepingcomputer.com/news/security/trust-wallet-says-7-million-crypto-theft-attack-drained-2-596-wallets [5] Agentic AI for Autonomous Defense in Software Supply Chain Security: Beyond Provenance to Vulnerability Mitigation arXiv · Research · https://arxiv.org/abs/2512.23480 [6] Fake MAS Windows activation domain used to spread PowerShell malware BleepingComputer · Analysis · https://bleepingcomputer.com/news/security/fake-mas-windows-activation-domain-used-to-spread-powershell-malware [7] CoTDeceptor:Adversarial Code Obfuscation Against CoT-Enhanced LLM Code Agents arXiv · Research · https://arxiv.org/abs/2512.21250 DAST [8] GoldenFuzz: Generative Golden Reference Hardware Fuzzing arXiv · Research · https://arxiv.org/abs/2512.21524 [9] Future of DAST: Why AI-Generated Code Demands a New Strategy Checkmarx · Analysis · https://checkmarx.com/blog/future-of-dast-why-ai-generated-code-demands-a-new-strategy REMEDIATION [10] Rethinking the Capability of Fine-Tuned Language Models for Automated Vulnerability Repair arXiv · Research · https://arxiv.org/abs/2512.22633 [11] MongoDB warns admins to patch severe vulnerability immediately BleepingComputer · Analysis · https://bleepingcomputer.com/news/security/mongodb-warns-admins-to-patch-severe-vulnerability-immediately TRUST [12] Adaptive Trust Consensus for Blockchain IoT: Comparing RL, DRL, and MARL Against Naive, Collusive, Adaptive, Byzantine, and Sleeper Attacks arXiv · Research · https://arxiv.org/abs/2512.22860 [13] Toward Secure and Compliant AI: Organizational Standards and Protocols for NLP Model Lifecycle Management arXiv · Research · https://arxiv.org/abs/2512.22060 [14] A Blockchain-Monitored Agentic AI Architecture for Trusted Perception-Reasoning-Action Pipelines arXiv · Research · https://arxiv.org/abs/2512.20985 [15] Operationalizing the CoSAI Risk Map (CoSAI-RM) CoSAI · Analysis · https://coalitionforsecureai.org/operationalizing-the-cosai-risk-map-cosai-rm MODELS [16] Jailbreaking Attacks vs. Content Safety Filters: How Far Are We in the LLM Safety Arms Race? arXiv · Research · https://arxiv.org/abs/2512.24044 [17] DivQAT: Enhancing Robustness of Quantized Convolutional Neural Networks against Model Extraction Attacks arXiv · Research · https://arxiv.org/abs/2512.23948 [18] Multilingual Hidden Prompt Injection Attacks on LLM-Based Academic Reviewing arXiv · Research · https://arxiv.org/abs/2512.23684 [19] EquaCode: A Multi-Strategy Jailbreak Approach for Large Language Models via Equation Solving and Code Completion arXiv · Research · https://arxiv.org/abs/2512.23173 AI SECURITY [20] Toward Trustworthy Agentic AI: A Multimodal Framework for Preventing Prompt Injection Attacks arXiv · Research · https://arxiv.org/abs/2512.23557 [21] Multi-Agent Framework for Threat Mitigation and Resilience in AI-Based Systems arXiv · Research · https://arxiv.org/abs/2512.23132 [22] It's a TRAP! Task-Redirecting Agent Persuasion Benchmark for Web Agents arXiv · Research · https://arxiv.org/abs/2512.23128 [23] AegisAgent: An Autonomous Defense Agent Against Prompt Injection Attacks in LLM-HARs arXiv · Research · https://arxiv.org/abs/2512.20986 ADVISORIES IN THIS WINDOW 39 npm advisories · 35 critical · 3 high · 1 moderate 14 PyPI advisories · 2 critical · 9 high · 3 moderate 13 Go advisories · 1 high · 10 moderate · 2 low 4 Packagist advisories · 2 high · 2 moderate 1 crates.io advisory · 1 moderate 1 RubyGems 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.