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 24 June 2026 · Retrospective · Covers 23 June 2026 00:00 to 24 June 2026 00:00 UTC

Read on the web

Top developments

LastPass confirms data breach in Klue supply chain attack

BleepingComputer · Incident · SCA

Malicious npm Packages Pose as PostCSS Tools to Deliver Windows RAT

The Hacker News · Research · SCA

The New Security Control Point: Governing AI Agents Inside the Execution Loop

Snyk · Research · AI Security, Trust

OpenAI Expands Daybreak With GPT-5.5-Cyber to Help Defenders Patch Security Flaws

The Hacker News · Advisory · Remediation

SCA

Bridging the Gap Between Code and Research: Why SCORED ’26 Matters for Open Source Security

OpenSSF · Analysis · SCA

GitHub Updates actions/checkout to Block Common Pwn Request Attack Patterns

The Hacker News · Analysis · SCA

What nearly 10,000 developer environments reveal about agentic development risk

Snyk · Analysis · Agentic SDLC, SCA

DAST

Red-Teaming the Agentic Red-Team

arXiv · Research · DAST, Models

Agentic SDLC

SoK: AI Secure Code Generation: Progress, Pitfalls, and Paths Forward

arXiv · Research · Agentic SDLC

Detecting AI Coding Agents in Open Source: A Validated Multi-Method Census of 180 Million Repositories

arXiv · Research · Agentic SDLC

Remediation

The Exploit Doesn't Exist. You Can Still Prove It Works Against You

BleepingComputer · Analysis · Remediation

From vulnerability report to CVE draft in minutes: how Elastic automated security advisories with AI

Elastic · Analysis · AI Security, Remediation

Chainguard Libraries for Java is now GA; CVE remediation beta available for sign up

Chainguard · Analysis · Remediation, SCA

Trust

Fifty Years of Specification Completeness: What Aviation Certification Tells AI Governance About Epoch Limits, Proof Surfaces, and the Structural Gap

arXiv · Research · Trust

What Does It Mean to Break a Distillation Defense?

arXiv · Research · Models, Trust

AI Security Priorities: A Field-Wide Agenda

arXiv · Research · Trust

Models

What Intermediate Layers Know: Detecting Jailbreaks from Entropy Dynamics

arXiv · Research · Models

PixJail: Self-Evolving Paper-to-Pipeline Reproduction for Text-to-Image Jailbreak Evaluation

arXiv · Research · Models

LLM Unlearning for Cyber Defense: A Survey on Methods, Challenges, and Emerging Threats

arXiv · Research · Models, Trust

AI Security

AI Threat Readiness Pillar 4: Detect and contain threats in real-time

Wiz · Analysis · AI Security

Poisoned Playbooks: Demystifying Knowledge Poisoning Effects on AI Security Agents

arXiv · Research · AI Security

Securing LLM-Agent Long-Term Memory Against Poisoning: Non-Malleable, Origin-Bound Authority with Machine-Checked Guarantees

arXiv · Research · AI Security

Advisories in this window

  • 45 npm advisories · 45 critical
  • 20 Go advisories · 3 critical · 7 high · 10 moderate
  • 17 Packagist advisories · 2 high · 12 moderate · 3 low
  • 12 PyPI advisories · 2 critical · 4 high · 6 moderate
  • 12 Maven advisories · 5 high · 7 moderate
  • 3 crates.io advisories · 1 high · 2 moderate
  • 1 Multi-ecosystem 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.