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, Monday 30 March 2026 · Retrospective · Covers 29 March 2026 00:00 to 30 March 2026 00:00 UTC

Read on the web

Top developments

Evaluating Prompt Injection Defenses for Educational LLM Tutors: Security-Usability-Latency Trade-offs

arXiv · Research · AI Security, Models

Python Vulnerability Lookup

Simon Willison · Analysis · Agentic SDLC

SNEAKDOOR: Stealthy Backdoor Attacks against Distribution Matching-based Dataset Condensation

arXiv · Research · Models

SCA

How Effective Are NPM Malicious Package Detectors? A Large-Scale Empirical Study

arXiv · Research · SCA

Agentic SDLC

Safer Builders, Risky Maintainers: A Comparative Study of Breaking Changes in Human vs Agentic PRs

arXiv · Research · Agentic SDLC

Models

Hidden Ads: Behavior Triggered Semantic Backdoors for Advertisement Injection in Vision Language Models

arXiv · Research · Models

AI Security

A Security Analysis of the OpenClaw AI Agent Framework

arXiv · Research · AI Security

Advisories in this window

  • 20 npm advisories · 2 critical · 5 high · 10 moderate · 3 low
  • 3 Packagist advisories · 1 high · 2 moderate
  • 2 Multi-ecosystem advisories · 1 moderate · 1 low
  • 2 Go advisories · 2 high
  • 1 GitHub Actions advisory · 1 critical
  • 1 crates.io advisory · 1 critical
  • 1 Maven advisory · 1 high

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.