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 2 November 2026 · Retrospective · Covers 1 November 2026 00:00 to 2 November 2026 00:00 UTC

Read on the web

Top developments

Trustworthy Execution of Industrial Agents

arXiv · Research · Trust

Decision Models as Policy Gates for Coding Agents: Explicit Policy Boundaries Improve Detection and Reduce False Alarms

arXiv · Research · Agentic SDLC, AI Security

HaloGuard 2.0: An Open-Weights Constitutional Output Guard for Multilingual Response Safety

arXiv · Research · Models

SCA

Alpine Linux rebuilds GitLab after attempted RCE attack

BleepingComputer · Analysis · SCA

Agentic SDLC

Launder-Bench: Can Repository-Level Agentic Code Laundering Be Detected?

arXiv · Research · Agentic SDLC

Step-Zero Attack: Agent Safety Before Observability

arXiv · Research · Agentic SDLC

AI Security

Beyond Prompt Injection: The Tool Update Gap in LLM Agent Security

arXiv · Research · AI Security

MemHarmBench: Evaluating Cross-Session Prompt Injection in Memory-Persistent AI Agents

arXiv · Research · AI Security

Advisories in this window

  • 4 npm advisories · 4 critical
  • 2 PyPI advisories · 2 critical
  • 1 RubyGems 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.