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, Thursday 17 September 2026 · Retrospective · Covers 16 September 2026 00:00 to 17 September 2026 00:00 UTC

Read on the web

Top developments

Google fixes actively exploited Android zero-day on Pixel devices

BleepingComputer · Incident · Remediation

Spain's data agency gets first report of AI-powered data breach

BleepingComputer · Incident · AI Security

One Extension Could Hijack AI Assistants Across Chrome, Comet, Edge, Opera Neon and Claude

The Hacker News · Incident · Agentic SDLC

SAST

A Security Risk Assessment Framework for AI-Powered Development Tools

arXiv · Research · Agentic SDLC, SAST

SCA

datasette 0.65.5

Simon Willison · Analysis · SCA

CASHEWS: Source Preprocessor for LLM-based Malicious Package Detection

arXiv · Research · AI Security, SCA

From Component Snapshots to Lifecycle Traces: Agent-Based Software Composition Analysis

arXiv · Research · SCA

DAST

AIJon: Automated Generation of Annotations for Fuzzing

arXiv · Research · DAST

PentestChain: A Cost-Aware, MCP-Orchestrated Framework for Automated Penetration Testing with Free-Tier LLMs

arXiv · Research · AI Security, DAST

Agentic SDLC

MAGS: Multi-agent Auto-formalization Guarantees Safety for Agentic Outputs

arXiv · Research · Agentic SDLC

Top Qodo Alternatives for AI-Powered Code Assistance

Aikido Security · Analysis · Agentic SDLC

Attacker Hijacks AI Coding Assistant Session, Spreads Shai-Hulud Across About 100 Repositories

The Hacker News · Analysis · Agentic SDLC

Remediation

datasette 1.0a40

Simon Willison · Analysis · Remediation

Trust

Zero Trust for AI Systems: Why Authorization Can’t Live Inside the Model

CoSAI · Research · Trust

Models

Beyond Routine Compliance: Cunning Data Cultivates Safety Vigilance in Large Language Models

arXiv · Research · Models

AI Security

AgentLSD: Evaluating AI Security Agents Under Adversarial Task Contamination

arXiv · Research · AI Security

Characterizing Network Centralization and Observability in the Remote MCP Ecosystem

arXiv · Research · AI Security

Securing quantum error correction against misleading advice from AI agents

arXiv · Research · AI Security

Advisories in this window

  • 45 npm advisories · 43 critical · 2 high
  • 19 PyPI advisories · 8 critical · 8 high · 3 moderate
  • 3 Packagist advisories · 3 moderate
  • 2 crates.io advisories · 2 high
  • 1 Go advisory · 1 moderate
  • 1 NuGet 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.