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, Tuesday 17 March 2026 Retrospective Covers 16 March 2026 00:00 to 17 March 2026 00:00 UTC Web: https://keryn.dev/headlines/daily/2026-03-17/ TOP DEVELOPMENTS [1] GlassWorm Attack Uses Stolen GitHub Tokens to Force-Push Malware Into Python Repos The Hacker News · Incident · https://thehackernews.com/2026/03/glassworm-attack-uses-stolen-github.html [2] CISA flags Wing FTP Server flaw as actively exploited in attacks BleepingComputer · Incident · https://bleepingcomputer.com/news/security/cisa-flags-wing-ftp-server-flaw-as-actively-exploited-in-attacks [3] CVE-2025-47813: Wing FTP Server Information Disclosure Vulnerability added to CISA's Known Exploited Vulnerabilities catalog CISA · Advisory · https://cisa.gov/known-exploited-vulnerabilities-catalog?search_api_fulltext=CVE-2025-47813 SAST [4] PCodeTrans: Translate Decompiled Pseudocode to Compilable and Executable Equivalent arXiv · Research · https://arxiv.org/abs/2603.14855 [5] Securing our codebase with autonomous agents Cursor · Analysis · https://cursor.com/blog/security-agents [6] Why Codex Security Doesn’t Include a SAST Report OpenAI News · Analysis · https://openai.com/index/why-codex-security-doesnt-include-sast SCA [7] Rethinking LLM Watermark Detection in Black-Box Settings: A Non-Intrusive Third-Party Framework arXiv · Research · https://arxiv.org/abs/2603.14968 DAST [8] Why Security Validation Is Becoming Agentic The Hacker News · Analysis · https://thehackernews.com/2026/03/why-security-validation-is-becoming.html AGENTIC SDLC [9] VibeContract: The Missing Quality Assurance Piece in Vibe Coding arXiv · Research · https://arxiv.org/abs/2603.15691 REMEDIATION [10] UK’s Companies House confirms security flaw exposed business data BleepingComputer · Analysis · https://bleepingcomputer.com/news/security/uks-companies-house-confirms-security-flaw-exposed-business-data TRUST [11] Governing frontier general-purpose AI in the public sector: adaptive risk management and policy capacity under uncertainty through 2030 arXiv · Research · https://arxiv.org/abs/2604.06215 [12] New Microsoft Purview innovations for Fabric to safely accelerate your AI transformation Microsoft · Analysis · https://techcommunity.microsoft.com/blog/microsoft-security-blog/new-microsoft-purview-innovations-for-fabric-to-safely-accelerate-your-ai-transf/4502156 MODELS [13] Evolving Contextual Safety in Multi-Modal Large Language Models via Inference-Time Self-Reflective Memory arXiv · Research · https://arxiv.org/abs/2603.15800 [14] TrinityGuard: A Unified Framework for Safeguarding Multi-Agent Systems arXiv · Research · https://arxiv.org/abs/2603.15408 [15] SFCoT: Safer Chain-of-Thought via Active Safety Evaluation and Calibration arXiv · Research · https://arxiv.org/abs/2603.15397 AI SECURITY [16] Amplification Effects in Test-Time Reinforcement Learning: Safety and Reasoning Vulnerabilities arXiv · Research · https://arxiv.org/abs/2603.15417 [17] How Vulnerable Are AI Agents to Indirect Prompt Injections? Insights from a Large-Scale Public Competition arXiv · Research · https://arxiv.org/abs/2603.15714 [18] Shadow AI is everywhere. Here’s how to find and secure it. BleepingComputer · Guide · https://bleepingcomputer.com/news/security/shadow-ai-is-everywhere-heres-how-to-find-and-secure-it ADVISORIES IN THIS WINDOW 50 npm advisories · 39 critical · 5 high · 4 moderate · 2 low 35 Go advisories · 2 critical · 10 high · 22 moderate · 1 low 18 PyPI advisories · 2 critical · 12 high · 2 moderate · 2 low 17 Packagist advisories · 1 critical · 7 high · 8 moderate · 1 low 2 Hex advisories · 1 high · 1 moderate 2 Maven advisories · 1 critical · 1 high 1 crates.io advisory · 1 high 1 Swift 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.