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, Friday 9 January 2026 Retrospective Covers 8 January 2026 00:00 to 9 January 2026 00:00 UTC Web: https://keryn.dev/headlines/daily/2026-01-09/ TOP DEVELOPMENTS [1] Cisco warns of Identity Service Engine flaw with exploit code BleepingComputer · Research · https://bleepingcomputer.com/news/security/cisco-warns-of-identity-service-engine-flaw-with-exploit-code [2] Researchers Uncover NodeCordRAT Hidden in npm Bitcoin-Themed Packages The Hacker News · Research · https://thehackernews.com/2026/01/researchers-uncover-nodecordrat-hidden.html [3] VMware ESXi zero-days likely exploited a year before disclosure BleepingComputer · Incident · https://bleepingcomputer.com/news/security/vmware-esxi-zero-days-likely-exploited-a-year-before-disclosure SCA [4] Deep Dive into the Abuse of DL APIs To Create Malicious AI Models and How to Detect Them arXiv · Research · https://arxiv.org/abs/2601.04553 REMEDIATION [5] Signal in the Noise: An Industry-Wide Perspective on the State of VEX OpenSSF · Analysis · https://openssf.org/blog/2026/01/08/signal-in-the-noise-an-industry-wide-perspective-on-the-state-of-vex [6] AI to defend critical infrastructure Anthropic · Analysis · https://anthropic.com/research/critical-infrastructure-defense [7] Cisco Patches ISE Security Vulnerability After Public PoC Exploit Release The Hacker News · Release · https://thehackernews.com/2026/01/cisco-patches-ise-security.html MODELS [8] Multi-turn Jailbreaking Attack in Multi-Modal Large Language Models arXiv · Research · https://arxiv.org/abs/2601.05339 [9] $PC^2$: Politically Controversial Content Generation via Jailbreaking Attacks on GPT-based Text-to-Image Models arXiv · Research · https://arxiv.org/abs/2601.05150 [10] Constitutional Classifiers++: Efficient Production-Grade Defenses against Universal Jailbreaks arXiv · Research · https://arxiv.org/abs/2601.04603 AI SECURITY [11] Defense Against Indirect Prompt Injection via Tool Result Parsing arXiv · Research · https://arxiv.org/abs/2601.04795 [12] Know Thy Enemy: Securing LLMs Against Prompt Injection via Diverse Data Synthesis and Instruction-Level Chain-of-Thought Learning arXiv · Research · https://arxiv.org/abs/2601.04666 [13] Autonomous Agents on Blockchains: Standards, Execution Models, and Trust Boundaries arXiv · Research · https://arxiv.org/abs/2601.04583 ADVISORIES IN THIS WINDOW 31 npm advisories · 19 critical · 5 high · 4 moderate · 3 low 9 PyPI advisories · 1 critical · 2 high · 6 moderate 5 crates.io advisories · 2 high · 2 moderate · 1 low 2 RubyGems advisories · 1 high · 1 moderate 2 Go advisories · 2 moderate 1 Swift advisory · 1 low 1 Multi-ecosystem advisory · 1 high 1 Packagist advisory · 1 moderate 1 Maven 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.