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 20 January 2026 · Retrospective · Covers 19 January 2026 00:00 to 20 January 2026 00:00 UTC

Read on the web

Top developments

Google Gemini Prompt Injection Flaw Exposed Private Calendar Data via Malicious Invites

The Hacker News · Research · AI Security

Fake ad blocker extension crashes the browser for ClickFix attacks

BleepingComputer · Analysis

Sockpuppetting: Jailbreaking LLMs by Combining Prefilling with Optimization

arXiv · Research · Models

SAST

OWASP PTK Integration with ZAP

ZAP (Checkmarx) · Analysis · DAST, SAST

SCA

Efficient Code Analysis via Graph Representation Learning-Guided Large Language Models

arXiv · Research · SCA

Docker Does Not Guarantee Reproducibility

arXiv · Research · SCA

Agentic SDLC

Prompt Injection Mitigation with Agentic AI, Nested Learning, and AI Sustainability via Semantic Caching

arXiv · Research · Agentic SDLC, AI Security

Models

In Vino Veritas and Vulnerabilities: Examining LLM Safety via Drunk Language Inducement

arXiv · Research · Models

KinGuard: Hierarchical Kinship-Aware Fingerprinting to Defend Against Large Language Model Stealing

arXiv · Research · Models

AI Security

MirrorGuard: Toward Secure Computer-Use Agents via Simulation-to-Real Reasoning Correction

arXiv · Research · AI Security

Rogue agents and shadow AI: Why VCs are betting big on AI security

TechCrunch: Security · Analysis · AI Security

Advisories in this window

  • 30 npm advisories · 30 critical
  • 2 Maven 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.