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 27 May 2026 · Retrospective · Covers 26 May 2026 00:00 to 27 May 2026 00:00 UTC

Read on the web

Top developments

CISA orders feds to patch actively exploited Drupal vulnerability

BleepingComputer · Incident · Remediation

KnowledgeDeliver LMS Flaw Exploited to Deploy Godzilla and Cobalt Strike

The Hacker News · Incident · Remediation

Microsoft Patches SharePoint RCE Flaw CVE-2026-45659 Across Server Versions

The Hacker News · Advisory · Remediation

SCA

Millions of AI agents imperiled by critical vulnerability in open source package

Ars Technica: Security · Analysis · AI Security, SCA

DAST

Comparing AI Application Security Testing Platforms

Doyensec · Analysis · AI Security, DAST

Lessons from Penetration Tests on Large-Scale Agent Systems

arXiv · Research · DAST

Batch Me If You Can: Coverage-guided RPKI Fuzzing at Scale

arXiv · Research · DAST

Agentic SDLC

Poison with Style: A Practical Poisoning Attack on Code Large Language Models

arXiv · Research · Agentic SDLC, Models

Microsoft Copilot Cowork Exfiltrates Files

Simon Willison · Analysis · Agentic SDLC, AI Security

SEC-bench Pro: Can Language Models Solve Long-Horizon Software Security Tasks?

arXiv · Research · Agentic SDLC

Remediation

Microsoft: Domain Controller lookup may fail on Windows Server 2016

BleepingComputer · Analysis · Remediation

CERT-In Recommends 12-Hour Patching for Internet-Facing Flaws Amid AI-Assisted Attacks

The Hacker News · Analysis · Remediation

Trust

How Varonis Atlas integrates Claude Compliance API for AI governance

BleepingComputer · Analysis · Trust

Models

BAIT: Boundary-Guided Disclosure Escalation LLM Jailbreaking via Self-Conditioned Reasoning

arXiv · Research · Models

Cordyceps: Covert Control Attacks on LLMs via Data Poisoning

arXiv · Research · AI Security, Models

GradSentry: Gradient Spectral Entropy for Backdoor Sample Filtering in Large Language Model Fine-Tuning

arXiv · Research · Models

AI Security

Prompt Injection Detection is Regime-Dependent: A Deployment-Aware Evaluation with Interpretable Structural Signals

arXiv · Research · AI Security

Cordon-MAS: Defending RAG against Knowledge Poisoning via Information-Flow Control

arXiv · Research · AI Security

Aligning Provenance with Authorization: A Dual-Graph Defense for LLM Agents

arXiv · Research · AI Security

Advisories in this window

  • 31 npm advisories · 18 critical · 7 high · 4 moderate · 2 low
  • 18 Maven advisories · 3 critical · 3 high · 9 moderate · 3 low
  • 14 Go advisories · 1 critical · 3 high · 7 moderate · 3 low
  • 9 Packagist advisories · 1 critical · 3 high · 1 moderate · 4 low
  • 9 PyPI advisories · 1 critical · 2 high · 5 moderate · 1 low

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.