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 10 January 2026 · Retrospective · Covers 9 January 2026 00:00 to 10 January 2026 00:00 UTC

Read on the web

Top developments

Trend Micro warns of critical Apex Central RCE vulnerability

BleepingComputer · Analysis · Remediation

Hackers target misconfigured proxies to access paid LLM services

BleepingComputer · Analysis · AI Security

Deepfake detectors are DUMB: A benchmark to assess adversarial training robustness under transferability constraints

arXiv · Research · Models

SAST

HogVul: Black-box Adversarial Code Generation Framework Against LM-based Vulnerability Detectors

arXiv · Research · Models, SAST

SCA

A Large Scale Empirical Analysis on the Adherence Gap between Standards and Tools in SBOM

arXiv · Research · SCA, Trust

LIDL: LLM Integration Defect Localization via Knowledge Graph-Enhanced Multi-Agent Analysis

arXiv · Research · SCA

DAST

Cybersecurity AI: A Game-Theoretic AI for Guiding Attack and Defense

arXiv · Research · AI Security, DAST

Agentic SDLC

Datadog uses Codex for system-level code review

OpenAI News · Analysis · Agentic SDLC

AI-BOM

AIBoMGen: Generating an AI Bill of Materials for Secure, Transparent, and Compliant Model Training

arXiv · Research · AI-BOM, Trust

Remediation

CISA Retires 10 Emergency Cybersecurity Directives Issued Between 2019 and 2024

The Hacker News · Analysis · Remediation

Models

The Echo Chamber Multi-Turn LLM Jailbreak

arXiv · Research · Models

PII-VisBench: Evaluating Personally Identifiable Information Safety in Vision Language Models Along a Continuum of Visibility

arXiv · Research · Models

FinVault: Benchmarking Financial Agent Safety in Execution-Grounded Environments

arXiv · Research · AI Security, Models

AI Security

VIGIL: Defending LLM Agents Against Tool Stream Injection via Verify-Before-Commit

arXiv · Research · AI Security

Memory Poisoning Attack and Defense on Memory Based LLM-Agents

arXiv · Research · AI Security

Advisories in this window

  • 21 npm advisories · 20 critical · 1 high
  • 7 PyPI advisories · 5 high · 2 low
  • 3 crates.io advisories · 2 high · 1 low
  • 3 Go advisories · 1 critical · 2 moderate
  • 3 Maven advisories · 2 critical · 1 moderate
  • 2 Packagist advisories · 2 moderate
  • 1 Swift advisory · 1 high
  • 1 NuGet advisory · 1 low

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.