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 1 October 2025 Retrospective Covers 30 September 2025 00:00 to 1 October 2025 00:00 UTC Web: https://keryn.dev/headlines/daily/2025-10-01/ TOP DEVELOPMENTS [1] Critical WD My Cloud bug allows remote command injection BleepingComputer · Advisory · https://bleepingcomputer.com/news/security/critical-wd-my-cloud-bug-allows-remote-command-injection [2] Researchers Disclose Google Gemini AI Flaws Allowing Prompt Injection and Cloud Exploits The Hacker News · Research · https://thehackernews.com/2025/09/researchers-disclose-google-gemini-ai.html [3] Nearly 50,000 Cisco firewalls vulnerable to actively exploited flaws BleepingComputer · Incident · https://bleepingcomputer.com/news/security/nearly-50-000-cisco-firewalls-vulnerable-to-actively-exploited-flaws SAST [4] Red Teaming Program Repair Agents: When Correct Patches can Hide Vulnerabilities arXiv · Research · https://arxiv.org/abs/2509.25894 AGENTIC SDLC [5] Lita: Light Agent Uncovers the Agentic Coding Capabilities of LLMs arXiv · Research · https://arxiv.org/abs/2509.25873 REMEDIATION [6] Chinese hackers exploiting VMware zero-day since October 2024 BleepingComputer · Analysis · https://bleepingcomputer.com/news/security/chinese-hackers-exploiting-vmware-zero-day-since-october-2024 [7] From Trace to Line: LLM Agent for Real-World OSS Vulnerability Localization arXiv · Research · https://arxiv.org/abs/2510.02389 [8] SecureBERT 2.0: Advanced Language Model for Cybersecurity Intelligence arXiv · Research · https://arxiv.org/abs/2510.00240 TRUST [9] SeedPrints: Fingerprints Can Even Tell Which Seed Your Large Language Model Was Trained From arXiv · Research · https://arxiv.org/abs/2509.26404 MODELS [10] Direct Token Optimization: A Self-contained Approach to Large Language Model Unlearning arXiv · Research · https://arxiv.org/abs/2510.00125 [11] SPATA: Systematic Pattern Analysis for Detailed and Transparent Data Cards arXiv · Research · https://arxiv.org/abs/2509.26640 [12] Fairness Testing in Retrieval-Augmented Generation: How Small Perturbations Reveal Bias in Small Language Models arXiv · Research · https://arxiv.org/abs/2509.26584 AI SECURITY [13] CHAI: Command Hijacking against embodied AI arXiv · Research · https://arxiv.org/abs/2510.00181 [14] Preventing Prompt Injection with Type-Directed Privilege Separation arXiv · Research · https://arxiv.org/abs/2509.25926 [15] Microsoft Expands Sentinel Into Agentic Security Platform With Unified Data Lake The Hacker News · Analysis · https://thehackernews.com/2025/09/microsoft-expands-sentinel-into-agentic.html ADVISORIES IN THIS WINDOW 8 Maven advisories · 8 moderate 7 npm advisories · 2 critical · 4 high · 1 moderate 5 Go advisories · 4 high · 1 moderate 1 NuGet advisory · 1 moderate 1 Packagist 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.