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 5 June 2026 Retrospective Covers 4 June 2026 00:00 to 5 June 2026 00:00 UTC Web: https://keryn.dev/headlines/daily/2026-06-05/ TOP DEVELOPMENTS [1] Hola Browser for Windows compromised to deliver cryptominer BleepingComputer · Incident · https://bleepingcomputer.com/news/security/hola-browser-for-windows-compromised-to-deliver-cryptominer [2] Claude Code GitHub Action Flaw Let One Malicious Issue Hijack Repositories The Hacker News · Incident · https://thehackernews.com/2026/06/claude-code-github-action-flaw-let-one.html [3] Credit card theft campaign abuses Stripe to host stolen payment info BleepingComputer · Incident · https://bleepingcomputer.com/news/security/credit-card-theft-campaign-abuses-stripe-to-host-stolen-payment-info SAST [4] AttackPathGNN: Cross-function vulnerability detection in smart contracts using state interference graphs and conjunction pooling arXiv · Research · https://arxiv.org/abs/2606.05986 DAST [5] ZERO-APT: A Closed-Loop Adversarial Framework for LLM-Driven Automated Penetration Testing under Intelligent Defense arXiv · Research · https://arxiv.org/abs/2606.05567 AGENTIC SDLC [6] Microskill Architecture: A Modular Skill-Driven Framework for AI-Native Code Generation arXiv · Research · https://arxiv.org/abs/2606.05720 [7] SmellBench: Towards Fine-Grained Evaluation of Code Agents on Refactoring Tasks arXiv · Research · https://arxiv.org/abs/2606.05574 REMEDIATION [8] Cisco warns of critical Unified CM flaw with PoC exploit code BleepingComputer · Analysis · https://bleepingcomputer.com/news/security/cisco-warns-of-critical-unified-cm-flaw-with-poc-exploit-code TRUST [9] Revisiting Sustainability by Design in AI Protocol Governance: An Empirical Review of Comparative DAO and Corporate-Led Standards for the SDGs arXiv · Research · https://arxiv.org/abs/2606.05667 MODELS [10] Steering Vectors are an Adversarial Attack Surface arXiv · Research · https://arxiv.org/abs/2606.05958 [11] Consistency Training Along the Transformer Stack arXiv · Research · https://arxiv.org/abs/2606.05817 [12] Membrane: A Self-Evolving Contrastive Safety Memory for LLM Agent Defense arXiv · Research · https://arxiv.org/abs/2606.05743 AI SECURITY [13] WebMCP Tool Surface Poisoning: Runtime Manipulation Attacks on LLM Agents arXiv · Research · https://arxiv.org/abs/2606.06387 [14] GuardNet: Ensemble Strategies of Shallow Neural Networks for Robust Prompt Injection and Jailbreak Detection arXiv · Research · https://arxiv.org/abs/2606.05566 [15] ThreatsDay Bulletin: AI Agents Gone Wrong, Sketchy C2 Tools, ClickFix Tricks, JS Backdoors & 20+ New Stories The Hacker News · Analysis · https://thehackernews.com/2026/06/threatsday-bulletin-ai-agents-gone.html ADVISORIES IN THIS WINDOW 18 PyPI advisories · 2 critical · 1 high · 6 moderate · 9 low 14 Packagist advisories · 1 critical · 1 high · 11 moderate · 1 low 10 npm advisories · 3 critical · 2 high · 4 moderate · 1 low 7 Go advisories · 2 high · 4 moderate · 1 low 2 RubyGems advisories · 2 moderate 2 Maven advisories · 1 critical · 1 moderate 2 crates.io advisories · 2 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.