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 27 September 2026 · Retrospective · Covers 26 September 2026 00:00 to 27 September 2026 00:00 UTC

Read on the web

Top developments

SharePoint RCE and MikroTik RouterOS Flaws Actively Exploited in the Wild

The Hacker News · Incident

VeriWeave Govern: Evidence-Gated Deterministic Runtime Governance for Enterprise AI Agents

arXiv · Research · Trust

ASCEND: Personal AI Agents for Autonomous Scientific Computing Across HPC Clusters and GPU Workstations

arXiv · Research · Agentic SDLC

Agentic SDLC

SWE-MILE: Asynchronous Potential-Induced Milestone Credit Assignment for Long-Horizon Software Engineering Agents

arXiv · Research · Agentic SDLC

VulContextBench: A Benchmark for Security Context Retrieval in Coding Agents

arXiv · Research · Agentic SDLC

Trust

A Solvable Theory of Pre-training Data Poisoning: Regime-Dependent Scaling Exponents

arXiv · Research · Models, Trust

Zero Trust for AI Agents Starts With Fixing Zero Visibility

The Hacker News · Analysis · Trust

Models

SameFact: The Same Safety Facts Lead to Different Responses Across Interfaces

arXiv · Research · Models

Trust the Brand, Lose Control: How Identity Hijacks LLM Agent Orchestration

arXiv · Research · Models

AnchorRep: Defending LLMs Against Cross-Model Adversarial Transfer via Representation Repulsion

arXiv · Research · Models

AI Security

Silent Failures in Agentic Security Evaluation: A Validated Harness for Tool-Call Mediation Under Indirect Prompt Injection

arXiv · Research · AI Security

Advisories in this window

  • 2 npm advisories · 2 critical
  • 1 PyPI 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.