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, Saturday 16 May 2026 · Retrospective · Covers 15 May 2026 00:00 to 16 May 2026 00:00 UTC

Read on the web

Top developments

Raising the bar: Quality, shared responsibility, and the future of GitHub’s bug bounty program

GitHub · Research · Remediation

CVE-2026-42897: Microsoft Exchange Server Cross-Site Scripting Vulnerability added to CISA's Known Exploited Vulnerabilities catalog

CISA · Advisory

Funnel Builder WordPress plugin bug exploited to steal credit cards

BleepingComputer · Incident

SAST

Compile-time Security Analysis and Optimization of Sensitive String Producers

arXiv · Research · Agentic SDLC, SAST

Detecting Privilege Escalation in Polyglot Microservices via Agentic Program Analysis

arXiv · Research · SAST

Agentic SDLC

SLEIGHT-Bench: A Benchmark of Evasion Attacks Against Agent Monitors

arXiv · Research · Agentic SDLC, Models

Building a general-purpose accessibility agent—and what we learned in the process

GitHub · Analysis · Agentic SDLC, Remediation

Trust

Pluralistic-Alignment Urbanism: Operationalizing a Right to AI for Inclusive Public Space

arXiv · Research · Trust

Formal Methods Meet LLMs: Auditing, Monitoring, and Intervention for Compliance of Advanced AI Systems

arXiv · Research · Trust

AI Debris: Residual Risk and the Afterlife of Failed AI Systems

arXiv · Research · Trust

Models

LymphNode: A Plug-and-Play Access Control Method for Deep Neural Networks

arXiv · Research · Models

PCDM: A Diffusion-Based Data Poisoning Attack Against Federated Learning Systems

arXiv · Research · Models

Compositional Jailbreaking: An Empirical Analysis of Mutator Chain Interactions in Aligned LLMs

arXiv · Research · Models

AI Security

FORGE: Self-Evolving Agent Memory With No Weight Updates via Population Broadcast

arXiv · Research · AI Security

A Cross-Modal Prompt Injection Attack against Large Vision-Language Models with Image-Only Perturbation

arXiv · Research · AI Security

Advisories in this window

  • 47 npm advisories · 40 critical · 6 high · 1 moderate
  • 9 Packagist advisories · 5 high · 4 moderate
  • 5 Go advisories · 2 high · 2 moderate · 1 low
  • 4 PyPI advisories · 2 high · 2 moderate
  • 3 Maven advisories · 3 high
  • 2 crates.io advisories · 1 high · 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.