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, Wednesday 4 November 2026 · Retrospective · Covers 3 November 2026 00:00 to 4 November 2026 00:00 UTC

Read on the web

Top developments

Google: LLMjacking attacks rack up $1 million in cloud AI charges

BleepingComputer · Incident · AI Security

Cyber chief: UK facing AI-powered attacks on critical infrastructure within two years

UK National Cyber Security Centre · Incident · AI Security

Red Hat Patches 9.8-Rated Linux TCP RCE Flaw While Ubuntu Releases Fixes for Testing

The Hacker News · Advisory · Remediation

Synology NAS Devices Targeted in Ransomware Attacks Exploiting Patched DSM Flaw

The Hacker News · Advisory · Remediation

SCA

Hardening GitHub Actions Against Outside Threats

Socket · Analysis · SCA

Composer 2.11 Adds Dependency Cooldowns

Socket · Release · SCA

Binance Reveals How Fake Job Interviews and AI Tool Abuse Led to $6.43 Billion Theft

The Hacker News · Analysis · SCA

Agentic SDLC

DoGNAVY-Exploit: Harnessing Parallel Open-Weight Agents for Stage-Aware Vulnerability Exploitation

arXiv · Research · Agentic SDLC

AI supply chain attacks: Old payloads, new entry points

Mend.io · Analysis · Agentic SDLC, SCA

Remediation

Barracuda warns of critical flaws allowing root access to devices

BleepingComputer · Analysis · Remediation, Trust

The PHP Security Wake-Up Call: Fixes Are Only the Beginning

OpenSSF · Analysis · Remediation

UEFI bootkit infected fully patched Windows machines. Is Microsoft to blame?

Ars Technica: Security · Analysis · Remediation

Trust

Whose Transparency is it Anyway? Understanding Generative AI Transparency Needs and Gaps Across Stakeholders

arXiv · Research · Trust

Stop Chasing CVEs: Start Governing Software Dependencies

Sonatype · Analysis · Remediation, SCA, Trust

Models

Extracting System Prompt of LLM Services in Complex (Agentic) Settings: Hierarchical Optimization and Reliable Evaluation Metrics

arXiv · Research · Models

BrainwashedLLM: Jailbreaking via Automated Adversarial Chain of Thoughts Discovery

arXiv · Research · Models

AI Security

Gartner Predicts SOCs Will Have 50% More Engineers Than Analysts by 2028

BleepingComputer · Analysis · AI Security

ScamWorld: An Interactive Environment for Evaluating Web Agents Against Online Fraud

arXiv · Research · AI Security

Right Tool, Wrong Parameters: Defending LLM Agents Against Parameter Poisoning

arXiv · Research · AI Security

Advisories in this window

  • 110 npm advisories · 109 critical · 1 high
  • 4 PyPI advisories · 3 critical · 1 high
  • 3 Go advisories · 1 high · 1 moderate · 1 low
  • 1 Maven advisory · 1 high
  • 1 NuGet advisory · 1 high
  • 1 RubyGems advisory · 1 critical

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.