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, Friday 28 August 2026 · Retrospective · Covers 27 August 2026 00:00 to 28 August 2026 00:00 UTC

Read on the web

Top developments

CISA orders feds to patch Citrix NetScaler RCE flaw by Saturday

BleepingComputer · Advisory · Remediation

Two Alleged ‘TeamPCP’ Hackers Arrested in Australia

Krebs on Security · Analysis · SCA

Breaking Claude Code Opus 5 Auto Mode

Embrace The Red · Research · Agentic SDLC, AI Security

Inside 90 days of attacks on AI infrastructure

Wiz · Incident · AI Security

Amazon Kiro Prompt Injection Can Exfiltrate Sensitive Data Through Kiro Powers

The Hacker News · Research · AI Security

SAST

KubeCap: A Framework for Capability Minimization in Kubernetes via Static Analysis and LLM-Assisted Rule Inference

arXiv · Research · SAST

SCA

Join OpenSSF at AGNTCon + MCPCon North America: Securing Agentic AI

OpenSSF · Analysis · SCA, Trust

OpenClaw went viral. Meet the maintainers building and securing it.

GitHub · Analysis · SCA

AROMA+: A Study of Factors Affecting Reproducible Builds in the Maven Ecosystem

arXiv · Research · SCA

Agentic SDLC

Claude Code Complete User Handbook

arXiv · Research · Agentic SDLC

Trust

Five Primitives for Governing Autonomous AI Agents at Runtime

arXiv · Research · Trust

Models

RedEvoAgent: Automatic Red-Teaming Agent with Experience-Driven Skill Evolution

arXiv · Research · AI Security, Models

Low-ASR Backdoors: Exploiting Attack Success Rate Reduction and Attacker-Defender Asymmetry

arXiv · Research · Models

Fully Unleashing the Multimodal Attacker: Meta-Adaptive Jailbreaking of Vision-Language Models

arXiv · Research · Models

AI Security

Nearly 700 rogue AI agents coordinated in the Hugging Face attack

BleepingComputer · Analysis · AI Security

100-plus companies call for ‘global surge’ in AI-powered cyber defense

CyberScoop · Analysis · AI Security

The Framing Gap: Indirect Prompt-Injection Exfiltration Defeats Surface-Level Defenses in Tool-Using Agents

arXiv · Research · AI Security

Advisories in this window

  • 31 npm advisories · 29 critical · 2 moderate
  • 8 PyPI advisories · 6 critical · 2 moderate
  • 4 Packagist advisories · 2 high · 1 moderate · 1 low
  • 3 Maven advisories · 3 critical
  • 2 Go advisories · 1 high · 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.