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, Sunday 15 November 2026 · Retrospective · Covers 14 November 2026 00:00 to 15 November 2026 00:00 UTC

Read on the web

Top developments

Cursor confirms security breach led to malicious Claude Code extension

BleepingComputer · Incident · Agentic SDLC, AI Security, SCA

Beware the New AI-Fueled Ransomware Boom

WIRED · Incident

Architecting the Corporate AI Infrastructure: The Evolving Roles of AI Governance Committees and Chief Ethics Officers

arXiv · Research · Trust

Agentic SDLC

Agent Authenticator: Passkey-Grade, Hardware-Bound Authentication for AI Agents

arXiv · Research · Agentic SDLC, Trust

When the Spec Sheet Lies: Injection Attacks on LLM-Generated Compliance Artifacts

arXiv · Research · Agentic SDLC, AI Security

Models

BadGCL: Towards Persistent Backdoor Attack on Graph Continual Learning Systems

arXiv · Research · Models

Steering Bayesian Inference and Decisions through Data Poisoning

arXiv · Research · Models

A Backdoor Trigger Is Legible in Fine-Tune Weights

arXiv · Research · Models

AI Security

Protecting the System, Stranding the User: The Limits of Multi-Agent Authorization

arXiv · Research · AI Security

Optional Traps: An Empirical Study of LLM Agents Against Credential Deception and Alert-Driven Revocation

arXiv · Research · AI Security

Advisories in this window

  • 10 PyPI advisories · 7 critical · 3 high
  • 2 npm advisories · 2 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.