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, Tuesday 9 June 2026 · Retrospective · Covers 8 June 2026 00:00 to 9 June 2026 00:00 UTC

Read on the web

Top developments

Check Point links VPN zero-day attacks to Qilin ransomware gang

BleepingComputer · Incident · Remediation

Over 20,000 Instagram accounts stolen in Meta AI support hack

BleepingComputer · Incident · AI Security

Gogs patches critical zero-day enabling remote code execution

BleepingComputer · Advisory · Remediation

Critical UniFi OS bug lets hackers gain root without authentication

BleepingComputer · Advisory · Remediation

One-Character Linux Kernel Flaw Enables Local Root Access, Exploits Now Public

The Hacker News · Research · Remediation

SAST

The Hardest Fork

The Hacker News · Analysis · SAST

SCA

New Shai-Hulud attack trojanizes 19 science-focused PyPI packages

BleepingComputer · Analysis · SCA

For the 2nd time in weeks, Microsoft packages laced with credential stealer

Ars Technica: Security · Analysis · Agentic SDLC, AI Security, SCA

Relocate and Emulate: Re-Hosting Android's Application Layer

arXiv · Research · SCA

Remediation

Hardening Agent Benchmarks with Adversarial Hacker-Fixer Loops

arXiv · Research · Models, Remediation

Anthropic’s Project Glasswing Update

Schneier on Security · Analysis · Remediation

Trust

Trustworthy Smart Fabs via Professional Proxies: Scaling Safe and Sustainable by Design (SSbD) through Industrial Data Spaces

arXiv · Research · Trust

Models

GRAFT: Graphlet-Triggered Backdoor Attack on GNN-Based Hardware Security Systems

arXiv · Research · Models

Safe-RULE: Safe Reinforcement UnLEarning

arXiv · Research · Models

Model Poisoning Against Federated Model Adaptation with Chain of Bit-Flips

arXiv · Research · Models

AI Security

PRISM: Recovering Instruction Sets from Language Model Activations

arXiv · Research · AI Security

Brain-Prompt Injection: A Route-Safety Audit for BCI-LLM Agents

arXiv · Research · AI Security

The Injection Paradox: Brand-Level Suppression in Safety-Trained LLM Recommendations via RAG Context Injection

arXiv · Research · AI Security, Models

Advisories in this window

  • 15 Maven advisories · 10 high · 3 moderate · 2 low
  • 11 Go advisories · 2 critical · 5 high · 4 low
  • 10 npm advisories · 6 critical · 1 high · 3 moderate
  • 6 PyPI advisories · 3 moderate · 3 low
  • 4 Hex advisories · 2 high · 2 moderate
  • 3 crates.io advisories · 3 high
  • 1 RubyGems advisory · 1 high
  • 1 Packagist advisory · 1 moderate

All advisories

Titles, links and short excerpts only; every item links to its source. Selection is automatic; the editor's note is AI-drafted and checked as described. Preview: the unsubscribe link and Keryn's postal address are added to each email when it is sent.