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 1 May 2026 · Retrospective · Covers 30 April 2026 00:00 to 1 May 2026 00:00 UTC

Read on the web

Top developments

New Linux ‘Copy Fail’ flaw gives hackers root on major distros

BleepingComputer · Analysis

Jailbroken Frontier Models Retain Their Capabilities

arXiv · Research · Models

That AI Extension Helping You Write Emails? It’s Reading Them First

Palo Alto Networks · Research

SAST

MCPHunt: An Evaluation Framework for Cross-Boundary Data Propagation in Multi-Server MCP Agents

arXiv · Research · AI Security, SAST

SCA

zkSBOM: Privacy-Preserving SBOM Sharing with Zero-Knowledge Sets

arXiv · Research · SCA, Trust

The Grand Software Supply Chain of AI Systems

arXiv · Research · SCA

PyTorch Lightning and Intercom-client Hit in Supply Chain Attacks to Steal Credentials

The Hacker News · Analysis · SCA

Agentic SDLC

GitHub Copilot CLI for Beginners: Interactive v. non-interactive mode

GitHub · Analysis · Agentic SDLC

Remediation

The most severe Linux threat to surface in years catches the world flat-footed

Ars Technica: Security · Analysis · Remediation

Trust

DEPTEX: Organization-First, Open Source Dependency Risk Monitoring

arXiv · Research · Trust

Test Before You Deploy: Governing Updates in the LLM Supply Chain

arXiv · Research · Trust

Models

Attention Is Where You Attack

arXiv · Research · Models

TwinGate: Stateful Defense against Decompositional Jailbreaks in Untraceable Traffic via Asymmetric Contrastive Learning

arXiv · Research · Models

Secret Stealing Attacks on Local LLM Fine-Tuning through Supply-Chain Model Code Backdoors

arXiv · Research · Models

AI Security

FlashRT: Towards Computationally and Memory Efficient Red-Teaming for Prompt Injection and Knowledge Corruption

arXiv · Research · AI Security

Latent Adversarial Detection: Adaptive Probing of LLM Activations for Multi-Turn Attack Detection

arXiv · Research · AI Security

Alignment Contracts for Agentic Security Systems

arXiv · Research · AI Security

Advisories in this window

  • 7 npm advisories · 4 critical · 2 high · 1 moderate
  • 7 Go advisories · 2 critical · 3 high · 1 moderate · 1 low
  • 6 PyPI advisories · 1 critical · 4 moderate · 1 low
  • 3 Packagist advisories · 2 high · 1 low
  • 3 Maven advisories · 1 critical · 2 moderate
  • 1 NuGet advisory · 1 moderate
  • 1 crates.io advisory · 1 high
  • 1 Multi-ecosystem advisory · 1 high

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.