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 24 March 2026 · Retrospective · Covers 23 March 2026 00:00 to 24 March 2026 00:00 UTC

Read on the web

Top developments

Trivy supply-chain attack spreads to Docker, GitHub repos

BleepingComputer · Incident · SCA

KICS GitHub Action Compromised: TeamPCP Strikes Again in Supply Chain Attack

Wiz · Incident · SCA

An AI-powered phishing campaign has compromised hundreds of organizations

CyberScoop · Incident

SAST

GitHub expands application security coverage with AI‑powered detections

GitHub · Analysis · SAST

SCA

Kusari Partners with OpenSSF to Strengthen Open Source Software Supply Chain Security

OpenSSF · Analysis · SCA

Quantifying Uncertainty in FMEDA Safety Metrics: An Error Propagation Approach for Enhanced ASIC Verification

arXiv · Research · SCA

Q-AGNN: Quantum-Enhanced Attentive Graph Neural Network for Intrusion Detection

arXiv · Research · SCA

Agentic SDLC

Are AI-assisted Development Tools Immune to Prompt Injection?

arXiv · Research · Agentic SDLC, AI Security

Early Discoveries of Algorithmist I: Promise of Provable Algorithm Synthesis at Scale

arXiv · Research · Agentic SDLC

Trust

Towards Secure Retrieval-Augmented Generation: A Comprehensive Review of Threats, Defenses and Benchmarks

arXiv · Research · Models, Trust

Models

Precision-Varying Prediction (PVP): Robustifying ASR systems against adversarial attacks

arXiv · Research · Models

SecureBreak -- A dataset towards safe and secure models

arXiv · Research · AI Security, Models

Structured Visual Narratives Undermine Safety Alignment in Multimodal Large Language Models

arXiv · Research · Models

AI Security

LLMON: An LLM-native Markup Language to Leverage Structure and Semantics at the LLM Interface

arXiv · Research · AI Security

Model Context Protocol Threat Modeling and Analyzing Vulnerabilities to Prompt Injection with Tool Poisoning

arXiv · Research · AI Security

Varonis Atlas: Securing AI and the Data That Powers It

BleepingComputer · Analysis · AI Security

Advisories in this window

  • 31 npm advisories · 24 critical · 4 high · 2 moderate · 1 low
  • 10 Packagist advisories · 1 critical · 5 high · 4 moderate
  • 9 RubyGems advisories · 1 high · 6 moderate · 2 low
  • 4 Go advisories · 1 critical · 1 high · 2 moderate
  • 3 PyPI advisories · 3 high
  • 2 Maven advisories · 1 moderate · 1 low
  • 1 Hex 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.