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 28 May 2026 · Retrospective · Covers 27 May 2026 00:00 to 28 May 2026 00:00 UTC

Read on the web

Top developments

Glassworm botnet disrupted after resilient C2 infrastructure takedown

BleepingComputer · Research · SCA

Malicious npm Package Stole Files From Claude AI User Directory via GitHub

The Hacker News · Incident · SCA

CVE-2026-8398: Daemon Tools Lite Embedded Malicious Code Vulnerability added to CISA's Known Exploited Vulnerabilities catalog

CISA · Advisory

SCA

S3C2 Summit 2025-07: Government Secure Supply Chain Summit

arXiv · Research · SCA

Blind PRNG Hijacking: An Undetectable Integrity-Preserving Attack Against LLM Watermarking

arXiv · Research · SCA

DAST

Cybersecurity AI (CAI) Dataset

arXiv · Research · DAST

Agentic SDLC

The Best-Laid SCHEMEs: Coordinated Sabotage and Monitoring in Multi-Agent Systems

arXiv · Research · Agentic SDLC

Towards Cybersecurity SuperIntelligence (CSI): What's the best harness for cybersecurity?

arXiv · Research · Agentic SDLC

SNARE: Adaptive Scenario Synthesis for Eliciting Overeager Behavior in Coding Agents

arXiv · Research · Agentic SDLC, Models

Trust

Code as a Weapon: A Consensus-Labeled Prompt Bank for Measuring Coding-Model Compliance with Malicious-Code Requests

arXiv · Research · Models, Trust

Mitigating Adaptive Attacks against Reasoning Models with Activation Consistency Training

arXiv · Research · AI Security, Models, Trust

Operational AI Deployment Assurance: Governance-State Orchestration Under Threshold-Sensitive Deployment Conditions -- A Governance Framework for High-Stakes AI Systems

arXiv · Research · Trust

Models

AIRGuard: Guarding Agent Actions with Runtime Authority Control

arXiv · Research · Models

Position: Retire the "Positive Backdoor" Label -- Secret Alignment Requires Strict and Systematic Evaluation

arXiv · Research · Models

Quantum-Enhanced Adversarial Robustness in Artificial Intelligence

arXiv · Research · Models

AI Security

Measuring Real-World Prompt Injection Attacks in LLM-based Resume Screening

arXiv · Research · AI Security

LACUNA: Safe Agents as Recursive Program Holes

arXiv · Research · AI Security

Technical Report: Exploring the Emerging Threats of the Agent Skill Ecosystem

arXiv · Research · AI Security

Advisories in this window

  • 26 Packagist advisories · 11 high · 10 moderate · 5 low
  • 20 Maven advisories · 3 critical · 3 high · 14 moderate
  • 18 npm advisories · 9 critical · 5 high · 4 moderate
  • 8 PyPI advisories · 1 critical · 5 high · 1 moderate · 1 low
  • 4 Go advisories · 3 high · 1 moderate
  • 1 crates.io advisory · 1 high
  • 1 RubyGems 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.