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, Thursday 16 July 2026 · Retrospective · Covers 15 July 2026 00:00 to 16 July 2026 00:00 UTC

Read on the web

Top developments

SonicWall customers under threat as attackers exploit 2 zero-days

CyberScoop · Research · Remediation

Microsoft patches bug in video game Age of Empires II

TechCrunch: Security · Advisory · Remediation

Researcher Drops New Windows Zero-Day PoC Hours After Microsoft Patch Tuesday

The Hacker News · Research · Remediation

GPT-Red: Unlocking Self-Improvement for Robustness

OpenAI News · Research · AI Security

SAST

ProfMalPlus: Agent-Coordinated Detection of Malicious NPM Packages via Static-Dynamic Analysis Synergy

arXiv · Research · SAST, SCA

DREA: Decoupled Reasoning and Exploration Agents for Repository-Level Vulnerability Detection

arXiv · Research · SAST

SCA

CHRONO-RESOLUTION: A Dependency Resolution Dataset at Release Points for npm, PyPI, and crates.io Packages

arXiv · Research · AI-BOM, SCA

Responding to the Five Eyes guidance on AI and cyber risk

Chainguard · Standard / policy · SCA

The npm Threat Landscape: Attack Surface and Mitigations (Updated July 15)

Palo Alto Networks · Analysis · SCA

DAST

Rethinking Penetration Testing for AI-Enabled Systems: From Resource Compromise to Behavioral Objective Violation

arXiv · Research · AI Security, DAST

Agentic SDLC

The Prover Is the Judge: Verified Security Software from AI Coding Agents in Ada/SPARK

arXiv · Research · Agentic SDLC, AI Security

Harness Engineering: Anatomy, Architecture, and Evolution of Coding Agents -- A Source-Code Study of Eleven Systems

arXiv · Research · Agentic SDLC

A Case-Bundle Operating Model for Coding Agents in OpenFOAM-Based CFD

arXiv · Research · Agentic SDLC

Remediation

Microsoft: Some Dell PCs shut down after recent Windows updates

BleepingComputer · Analysis · Remediation

Firefox, Chrome, Adobe, and VMware Updates Fix Multiple Critical Security Flaws

The Hacker News · Analysis · Remediation

Trust

Traccia: An OpenTelemetry-Based Governance Platform for AI Systems

arXiv · Research · AI Security, Trust

The US is advancing AI safety through state and federal action

OpenAI News · Analysis · Trust

Models

ToolAlignBench: Investigating Alignment Conflicts in Tool-Calling Enabled LLMs

arXiv · Research · Models

Inference-Time Concept Suppression and Video-Centric Evaluation for Text-to-Video Models

arXiv · Research · Models

Evaluating Frontier AI Agents as Autonomous Clinical Security Auditors

arXiv · Research · AI Security, Models

AI Security

Agent Skill Security: Threat Models, Attacks, Defenses, and Evaluation

arXiv · Research · AI Security

How I tricked Claude into leaking your deepest, darkest secrets

Simon Willison · Analysis · AI Security

How Agents Ask for Permission: User Permissions for AI Agents, from Interfaces to Enforcement

arXiv · Research · AI Security

Advisories in this window

  • 46 npm advisories · 41 critical · 4 high · 1 moderate
  • 15 Packagist advisories · 3 critical · 4 high · 8 moderate
  • 10 PyPI advisories · 1 critical · 7 high · 2 moderate
  • 6 Go advisories · 2 high · 2 moderate · 2 low
  • 6 RubyGems advisories · 2 high · 4 moderate
  • 1 NuGet advisory · 1 high
  • 1 Maven advisory · 1 high
  • 1 crates.io advisory · 1 moderate
  • 1 Hex 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.