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 5 March 2026 · Retrospective · Covers 4 March 2026 00:00 to 5 March 2026 00:00 UTC

Read on the web

Top developments

Fake Laravel Packages on Packagist Deploy RAT on Windows, macOS, and Linux

The Hacker News · Research · SCA

Mail2Shell zero-click attack lets hackers hijack FreeScout mail servers

BleepingComputer · Incident

US and EU police shut down LeakBase, a site accused of sharing stolen passwords and hacking tools

TechCrunch: Security · Incident

Agentic SDLC

Internal Safety Collapse in LLMs and Coding Agents

arXiv · Research · Agentic SDLC, Models

Remediation

Lock and unlock draft repository security advisories

GitHub · Analysis · Remediation

Cisco warns of max severity Secure FMC flaws giving root access

BleepingComputer · Analysis · Remediation

Code Fingerprints: Disentangled Attribution of LLM-Generated Code

arXiv · Research · Remediation

Trust

Steering Frozen LLMs: Adaptive Social Alignment via Online Prompt Routing

arXiv · Research · Models, Trust

New RFP Template for AI Usage Control and AI Governance

The Hacker News · Analysis · Trust

Models

Efficient Refusal Ablation in LLM through Optimal Transport

arXiv · Research · Models

Tuning Just Enough: Lightweight Backdoor Attacks on Multi-Encoder Diffusion Models

arXiv · Research · Models

When Safety Becomes a Vulnerability: Exploiting LLM Alignment Homogeneity for Transferable Blocking in RAG

arXiv · Research · AI Security, Models

AI Security

The MCP AuthN/Z Nightmare

Doyensec · Analysis · AI Security

MIND: Unified Inquiry and Diagnosis RL with Criteria Grounded Clinical Supports for Psychiatric Consultation

arXiv · Research · AI Security

Image-based Prompt Injection: Hijacking Multimodal LLMs through Visually Embedded Adversarial Instructions

arXiv · Research · AI Security, Models

Advisories in this window

  • 23 npm advisories · 3 critical · 8 high · 10 moderate · 2 low
  • 10 Go advisories · 3 critical · 5 high · 2 moderate
  • 8 PyPI advisories · 7 high · 1 moderate
  • 8 crates.io advisories · 2 critical · 3 high · 3 moderate
  • 8 Packagist advisories · 2 high · 5 moderate · 1 low
  • 4 Maven advisories · 1 critical · 2 high · 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.