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, Sunday 1 March 2026 · Retrospective · Covers 28 February 2026 00:00 to 1 March 2026 00:00 UTC

Read on the web

Top developments

ClawJacked Flaw Lets Malicious Sites Hijack Local OpenClaw AI Agents via WebSocket

The Hacker News · Incident · AI Security

MIDAS: Multi-Image Dispersion and Semantic Reconstruction for Jailbreaking MLLMs

arXiv · Research · Models

Pragma-VL: Towards a Pragmatic Arbitration of Safety and Helpfulness in MLLMs

arXiv · Research · Models

Models

ROKA: Robust Knowledge Unlearning against Adversaries

arXiv · Research · Models

AI Security

From Goals to Aspects, Revisited: An NFR Pattern Language for Agentic AI Systems

arXiv · Research · AI Security

Advisories in this window

  • 4 Go advisories · 1 critical · 1 high · 2 moderate
  • 3 npm advisories · 2 high · 1 low
  • 2 Maven advisories · 2 moderate
  • 1 crates.io advisory · 1 moderate
  • 1 PyPI 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.