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, Thursday 4 June 2026 Retrospective Covers 3 June 2026 00:00 to 4 June 2026 00:00 UTC Web: https://keryn.dev/headlines/daily/2026-06-04/ TOP DEVELOPMENTS [1] VS Code zero-day lets hackers steal GitHub tokens in one click BleepingComputer · Research · https://bleepingcomputer.com/news/security/vs-code-zero-day-lets-hackers-steal-github-tokens-in-one-click [2] New 'HTTP/2 Bomb' DoS attack crashes web servers in under a minute BleepingComputer · Analysis · https://bleepingcomputer.com/news/security/new-http-2-bomb-dos-attack-crashes-web-servers-in-under-a-minute [3] Acer working to patch max severity zero-days in Wave 7 routers BleepingComputer · Advisory · https://bleepingcomputer.com/news/security/acer-warns-of-max-severity-zero-days-affecting-wave-7-routers SAST [4] Revisiting Vul-RAG: Reproducibility and Replicability of RAG-based Vulnerability Detection with Open-Weight Models arXiv · Research · https://arxiv.org/abs/2606.04739 SCA [5] CyberGym-E2E: Scalable Real-World Benchmark for AI Agents' End-to-End Cybersecurity Capabilities arXiv · Research · https://arxiv.org/abs/2606.04460 DAST [6] What 345 Days of Untested Exposure Looks Like at a Bank BleepingComputer · Analysis · https://bleepingcomputer.com/news/security/what-345-days-of-untested-exposure-looks-like-at-a-bank AGENTIC SDLC [7] From Prompt to Process: a Process Taxonomy and Comparative Assessment of Frameworks Supporting AI Software Development Agents arXiv · Research · https://arxiv.org/abs/2606.04967 REMEDIATION [8] Beyond the Zero-Day: See Your Network Like an Attacker | Webinar with HD Moore The Hacker News · Analysis · https://thehackernews.com/2026/06/beyond-zero-day-see-your-network-like.html TRUST [9] Updates from Europe: Single Reporting Platform, Public Consultations, New Publications OpenSSF · Analysis · https://openssf.org/policy/2026/06/03/updates-from-europe-single-reporting-platform-public-consultations-new-publications [10] Provably Auditable and Safe LLM Agents from Human-Authored Ontologies arXiv · Research · https://arxiv.org/abs/2606.04903 [11] A blueprint for democratic governance of frontier AI OpenAI News · Analysis · https://openai.com/index/frontier-safety-blueprint MODELS [12] Willing but Unable: Separating Refusal from Capability in Code LLMs via Abliteration arXiv · Research · https://arxiv.org/abs/2606.05396 [13] Sequential Data Poisoning in LLM Post-Training arXiv · Research · https://arxiv.org/abs/2606.04929 AI SECURITY [14] Description-Code Inconsistency in Real-world MCP Servers: Measurement, Detection, and Security Implications arXiv · Research · https://arxiv.org/abs/2606.04769 [15] What If Prompt Injection Never Left? Rethinking Agent Security through Cross-Session Stored Prompt Injection arXiv · Research · https://arxiv.org/abs/2606.04425 [16] From Untrusted Input to Trusted Memory: A Systematic Study of Memory Poisoning Attacks in LLM Agents arXiv · Research · https://arxiv.org/abs/2606.04329 ADVISORIES IN THIS WINDOW 20 PyPI advisories · 4 critical · 6 high · 7 moderate · 3 low 13 npm advisories · 4 critical · 5 high · 2 moderate · 2 low 4 Packagist advisories · 3 high · 1 moderate 3 Go advisories · 1 high · 1 moderate · 1 low 1 Maven 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.