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 31 December 2025 Retrospective Covers 30 December 2025 00:00 to 31 December 2025 00:00 UTC Web: https://keryn.dev/headlines/daily/2025-12-31/ 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] Language Model Agents Under Attack: A Cross Model-Benchmark of Profit-Seeking Behaviors in Customer Service arXiv · Research · https://arxiv.org/abs/2512.24415 SCA [4] SourceBroken: A large-scale analysis on the (un)reliability of SourceRank in the PyPI ecosystem arXiv · Research · https://arxiv.org/abs/2512.24400 MODELS [5] The Silicon Psyche: Anthropomorphic Vulnerabilities in Large Language Models arXiv · Research · https://arxiv.org/abs/2601.00867 [6] Jailbreaking Attacks vs. Content Safety Filters: How Far Are We in the LLM Safety Arms Race? arXiv · Research · https://arxiv.org/abs/2512.24044 [7] DivQAT: Enhancing Robustness of Quantized Convolutional Neural Networks against Model Extraction Attacks arXiv · Research · https://arxiv.org/abs/2512.23948 AI SECURITY [8] 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 [9] Security teams debate how much to trust AI Help Net Security · Analysis · https://helpnetsecurity.com/2025/12/30/ai-security-threats-readiness ADVISORIES IN THIS WINDOW 39 npm advisories · 35 critical · 1 high · 3 moderate 5 Packagist advisories · 3 high · 2 low 4 PyPI advisories · 3 high · 1 moderate 3 Go advisories · 2 moderate · 1 low 2 crates.io advisories · 1 critical · 1 high 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.