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, Tuesday 21 July 2026 · Retrospective · Covers 20 July 2026 00:00 to 21 July 2026 00:00 UTC

Read on the web

Top developments

JadePuffer agentic attacks now target AI model data with ransomware

BleepingComputer · Incident · AI Security

Cursor, Codex, Gemini CLI, Antigravity hit by sandbox escapes

BleepingComputer · Research · Agentic SDLC

Hackers are exploiting recently patched WordPress bugs, putting millions of websites at risk

TechCrunch: Security · Advisory · Remediation

DAST

KernelDiag: Agent-Based Root Cause Diagnosis for Kernel Crashes

arXiv · Research · DAST

Agentic SDLC

RECEIPT: Deterministic, Reward-Hacking-Resistant Verification for White-Box Agentic XSS Discovery

arXiv · Research · Agentic SDLC

CORVUS: Context Optimization and Reduction Via Underlying Synchronization for LLM Coding Agents

arXiv · Research · Agentic SDLC

Why blocking AI models won’t stop the cyber threats they create

CyberScoop · Analysis · Agentic SDLC, Remediation

Remediation

Windows KB5121767 OOB update fixes shutdowns on some Dell PCs

BleepingComputer · Analysis · Remediation

Trust

An approach to systemic risks of AI through the lens of emergence, collective action problems, and externalities

arXiv · Research · Trust

Models

The Chronos Vulnerability: A Taxonomy of Temporal Persistence and Memory-Based Deception in Agentic AI

arXiv · Research · Models

LLM Safety Alignment in Low-Resource Languages: A Systematic Literature Review

arXiv · Research · Models

JailMeter: An Evidence-Based Evaluation Framework for Jailbreak Attacks on Large Language Models

arXiv · Research · Models

AI Security

ChainWatch: A Kill Chain-Aligned Sequential Detection Framework for Multi-Step Attacks in MCP-Based AI Agent Systems

arXiv · Research · AI Security

Trusted Credentials, Untrusted Behavior: Benchmarking LLM-Agent Security in High-Performance Computing

arXiv · Research · AI Security

Adaptive Adversaries: A Multi-Turn, Multi-LLM Benchmark for LLM Agent Security

arXiv · Research · AI Security

Advisories in this window

  • 272 NuGet advisories · 263 critical · 8 high · 1 moderate
  • 122 npm advisories · 97 critical · 9 high · 12 moderate · 4 low
  • 29 PyPI advisories · 2 critical · 15 high · 12 moderate
  • 8 Packagist advisories · 1 high · 7 moderate
  • 7 Go advisories · 3 high · 3 moderate · 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.