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, Tuesday 26 May 2026 · Retrospective · Covers 25 May 2026 00:00 to 26 May 2026 00:00 UTC

Read on the web

Top developments

Curriculum Learning for Safety Alignment

arXiv · Research · Models

AgentSecBench: Measuring Prompt Injection, Privacy Leakage, and Tool-Use Integrity in LLM Agents

arXiv · Research · AI Security

Anthropic’s restricted Claude Mythos model may be coming to Claude Code

BleepingComputer · Analysis · Agentic SDLC

SAST

Heimdall: Formally Verified Automated Migration of Legacy eBPF Programs to Rust

arXiv · Research · SAST

Trust

Proof of Useful Attestation: A Consensus Primitive for Attestation-Native Chains

arXiv · Research · Trust

Models

Building an Adversarial Malware Dataset by Family and Type: Generation, Evasion, and Poisoning Evaluation

arXiv · Research · Models

AI Security

How Agentic AI Coding Assistants Become the Attacker's Shell

arXiv · Research · AI Security

Advisories in this window

  • 63 npm advisories · 63 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.