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 30 May 2025 Retrospective Covers 29 May 2025 00:00 to 30 May 2025 00:00 UTC Web: https://keryn.dev/headlines/daily/2025-05-30/ TOP DEVELOPMENTS [1] Cybercriminals exploit AI hype to spread ransomware, malware BleepingComputer · Incident · https://bleepingcomputer.com/news/security/cybercriminals-exploit-ai-hype-to-spread-ransomware-malware [2] LLM Agents Should Employ Security Principles arXiv · Research · https://arxiv.org/abs/2505.24019 [3] The Automated but Risky Game: Modeling and Benchmarking Agent-to-Agent Negotiations and Transactions in Consumer Markets arXiv · Research · https://arxiv.org/abs/2506.00073 TRUST [4] Resecurity Compliance Manager empowers cybersecurity leaders with AI-driven insights Help Net Security · Analysis · https://helpnetsecurity.com/2025/05/29/resecurity-compliance-manager MODELS [5] MCP Safety Training: Learning to Refuse Falsely Benign MCP Exploits using Improved Preference Alignment arXiv · Research · https://arxiv.org/abs/2505.23634 [6] Merge Hijacking: Backdoor Attacks to Model Merging of Large Language Models arXiv · Research · https://arxiv.org/abs/2505.23561 [7] Disrupting Vision-Language Model-Driven Navigation Services via Adversarial Object Fusion arXiv · Research · https://arxiv.org/abs/2505.23266 AI SECURITY [8] Securing AI Agents with Information-Flow Control arXiv · Research · https://arxiv.org/abs/2505.23643 ADVISORIES IN THIS WINDOW 16 npm advisories · 14 critical · 2 moderate 4 Go advisories · 1 critical · 2 high · 1 moderate 3 PyPI advisories · 1 moderate · 2 low 1 Maven advisory · 1 low 1 Packagist advisory · 1 high 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.