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 11 March 2026 · Retrospective · Covers 10 March 2026 00:00 to 11 March 2026 00:00 UTC

Read on the web

Top developments

Microsoft’s monthly Patch Tuesday is first in 6 months with no actively exploited zero-days

CyberScoop · Advisory · Remediation

CISA: Recently patched Ivanti EPM flaw now actively exploited

BleepingComputer · Advisory · Remediation

CISA Flags SolarWinds, Ivanti, and Workspace One Vulnerabilities as Actively Exploited

The Hacker News · Incident

SAST

MCP-in-SoS: Risk assessment framework for open-source MCP servers

arXiv · Research · AI Security, SAST

Compatibility at a Cost: Systematic Discovery and Exploitation of MCP Clause-Compliance Vulnerabilities

arXiv · Research · AI Security, SAST

Agentic SDLC

CR-Bench: Evaluating the Real-World Utility of AI Code Review Agents

arXiv · Research · Agentic SDLC

Remediation

Microsoft March 2026 Patch Tuesday fixes 2 zero-days, 79 flaws

BleepingComputer · Advisory · Remediation

Microsoft releases Windows 10 KB5078885 extended security update

BleepingComputer · Analysis · Remediation

Windows 11 KB5079473 & KB5078883 cumulative updates released

BleepingComputer · Analysis · Remediation

Trust

Quality-Driven Agentic Reasoning for LLM-Assisted Software Design: Questions-of-Thoughts (QoT) as a Time-Series Self-QA Chain

arXiv · Research · Trust

AWS European Sovereign Cloud achieves first compliance milestone: SOC 2 and C5 reports plus seven ISO certifications

AWS Security Blog · Standard / policy · Trust

Models

DIVE: Scaling Diversity in Agentic Task Synthesis for Generalizable Tool Use

arXiv · Research · Models

Multi-Stream Perturbation Attack: Breaking Safety Alignment of Thinking LLMs Through Concurrent Task Interference

arXiv · Research · Models

Removing the Trigger, Not the Backdoor: Alternative Triggers and Latent Backdoors

arXiv · Research · Models

AI Security

The Bureaucracy of Speed: Structural Equivalence Between Memory Consistency Models and Multi-Agent Authorization Revocation

arXiv · Research · AI Security

Mandiant’s founder just raised $190M for his autonomous AI agent security startup

TechCrunch: Security · Analysis · AI Security

Improving instruction hierarchy in frontier LLMs

OpenAI News · Analysis · AI Security

Advisories in this window

  • 43 npm advisories · 31 critical · 8 high · 4 moderate
  • 11 Packagist advisories · 4 high · 4 moderate · 3 low
  • 9 Go advisories · 1 critical · 2 high · 6 moderate
  • 4 NuGet advisories · 4 moderate
  • 3 PyPI advisories · 1 critical · 1 high · 1 moderate
  • 3 Maven advisories · 2 moderate · 1 low
  • 1 Multi-ecosystem advisory · 1 high
  • 1 RubyGems advisory · 1 moderate
  • 1 crates.io 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.