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, Saturday 14 June 2025 Retrospective Covers 13 June 2025 00:00 to 14 June 2025 00:00 UTC Web: https://keryn.dev/headlines/daily/2025-06-14/ TOP DEVELOPMENTS [1] Apple Zero-Click Flaw in Messages Exploited to Spy on Journalists Using Paragon Spyware The Hacker News · Incident · https://thehackernews.com/2025/06/apple-zero-click-flaw-in-messages.html [2] Shadow AI: Examples, Risks, and 8 Ways to Mitigate Them Mend.io · Research · https://mend.io/blog/shadow-ai-examples-risks-and-8-ways-to-mitigate-them [3] Discord flaw lets hackers reuse expired invites in malware campaign BleepingComputer · Incident · https://bleepingcomputer.com/news/security/discord-flaw-lets-hackers-reuse-expired-invites-in-malware-campaign SAST [4] Identifying Helpful Context for LLM-based Vulnerability Repair: A Preliminary Study arXiv · Research · https://arxiv.org/abs/2506.11561 REMEDIATION [5] SEC-bench: Automated Benchmarking of LLM Agents on Real-World Software Security Tasks arXiv · Research · https://arxiv.org/abs/2506.11791 [6] SoK: Automated Vulnerability Repair: Methods, Tools, and Assessments arXiv · Research · https://arxiv.org/abs/2506.11697 MODELS [7] InfoFlood: Jailbreaking Large Language Models with Information Overload arXiv · Research · https://arxiv.org/abs/2506.12274 [8] Investigating Vulnerabilities and Defenses Against Audio-Visual Attacks: A Comprehensive Survey Emphasizing Multimodal Models arXiv · Research · https://arxiv.org/abs/2506.11521 AI SECURITY [9] Mitigating prompt injection attacks with a layered defense strategy Google · Analysis · https://security.googleblog.com/2025/06/mitigating-prompt-injection-attacks.html [10] DRIFT: Dynamic Rule-Based Defense with Injection Isolation for Securing LLM Agents arXiv · Research · https://arxiv.org/abs/2506.12104 ADVISORIES IN THIS WINDOW 10 Packagist advisories · 9 moderate · 1 low 10 Maven advisories · 6 high · 4 moderate 9 PyPI advisories · 1 critical · 2 high · 6 moderate 2 RubyGems advisories · 1 critical · 1 high 1 npm advisory · 1 critical 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.