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 21 January 2026 Retrospective Covers 20 January 2026 00:00 to 21 January 2026 00:00 UTC Web: https://keryn.dev/headlines/daily/2026-01-21/ TOP DEVELOPMENTS [1] Evelyn Stealer Malware Abuses VS Code Extensions to Steal Developer Credentials and Crypto The Hacker News · Research · https://thehackernews.com/2026/01/evelyn-stealer-malware-abuses-vs-code.html [2] Tokenomics: Quantifying Where Tokens Are Used in Agentic Software Engineering arXiv · Research · https://arxiv.org/abs/2601.14470 [3] Unpacking Security Scanners for GitHub Actions Workflows arXiv · Research · https://arxiv.org/abs/2601.14455 SAST [4] An Empirical Study on Remote Code Execution in Machine Learning Model Hosting Ecosystems arXiv · Research · https://arxiv.org/abs/2601.14163 SCA [5] Understanding NYDFS and why it matters Chainguard · Analysis · https://chainguard.dev/unchained/understanding-nydfs-and-why-it-matters REMEDIATION [6] AI-supported vulnerability triage with the GitHub Security Lab Taskflow Agent GitHub · Analysis · https://github.blog/security/ai-supported-vulnerability-triage-with-the-github-security-lab-taskflow-agent [7] VulnResolver: A Hybrid Agent Framework for LLM-Based Automated Vulnerability Issue Resolution arXiv · Research · https://arxiv.org/abs/2601.13933 TRUST [8] Strengthen your supply chain with code-to-cloud traceability and SLSA Build Level 3 security GitHub · Analysis · https://github.blog/changelog/2026-01-20-strengthen-your-supply-chain-with-code-to-cloud-traceability-and-slsa-build-level-3-security MODELS [9] VirtualCrime: Evaluating the Criminal Potential and Agentic Behaviors of Large Language Models via Sandbox Simulation arXiv · Research · https://arxiv.org/abs/2601.13981 [10] Turn-Based Structural Triggers: Structure-Conditioned Backdoors in Multi-Turn LLMs arXiv · Research · https://arxiv.org/abs/2601.14340 [11] RECAP: A Resource-Efficient Method for Adversarial Prompting in Large Language Models arXiv · Research · https://arxiv.org/abs/2601.15331 AI SECURITY [12] PINA: Prompt Injection Attack against Navigation Agents arXiv · Research · https://arxiv.org/abs/2601.13612 [13] Securing the AI Agent Revolution: A Practical Guide to Model Context Protocol Security CoSAI · Guide · https://coalitionforsecureai.org/securing-the-ai-agent-revolution-a-practical-guide-to-mcp-security [14] Three Flaws in Anthropic MCP Git Server Enable File Access and Code Execution The Hacker News · Analysis · https://thehackernews.com/2026/01/three-flaws-in-anthropic-mcp-git-server.html ADVISORIES IN THIS WINDOW 29 npm advisories · 24 critical · 2 high · 1 moderate · 2 low 8 Go advisories · 2 critical · 4 high · 2 moderate 6 Packagist advisories · 3 moderate · 3 low 4 PyPI advisories · 4 high 3 Maven advisories · 2 critical · 1 moderate 1 NuGet 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.