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, Friday 10 July 2026 · Retrospective · Covers 9 July 2026 00:00 to 10 July 2026 00:00 UTC

Read on the web

Top developments

Microsoft patches RoguePlanet Defender zero-day vulnerability

BleepingComputer · Advisory · Remediation

GhostApproval Symlink Flaws Could Let Malicious Repos Run Code in AI Coding Agents

The Hacker News · Research · Agentic SDLC, AI Security

GodDamn Ransomware Uses PoisonX Driver to Disable Endpoint Defenses

The Hacker News · Incident

SAST

Toward Inferring Accurate Context-free Grammars for Big Languages in a Black-box Setting

arXiv · Research · DAST, SAST

SeedSmith: LLM-Driven Seed Synthesis for Directed Fuzzing

arXiv · Research · Agentic SDLC, SAST

SCA

Injective SDK on npm infected with cryptocurrency wallet stealer

BleepingComputer · Analysis · SCA

npm 12 Disables Install Scripts by Default to Reduce Supply Chain Risk

The Hacker News · Analysis · SCA

Agentic SDLC

Top AI Agents Built to Catch Malicious Code Can Be Tricked Into Running It

The Hacker News · Analysis · Agentic SDLC, AI Security

Remediation

Patch for Windows Defender 0-day could allow attackers to fill hard disk

Ars Technica: Security · Analysis · Remediation

Microsoft expects more Windows security updates from AI-discovered flaws

BleepingComputer · Analysis · Remediation

Trust

Proof-of-Continuity: A Temporal Model for Authority Propagation in Distributed Systems and AI Agents

arXiv · Research · Trust

Models

Optimizing Against Safety Representations: Activation-Guided Adversarial Suffixes and the Geometry of Refusal

arXiv · Research · Models

Persuasion Attacks Can Decrease Effectiveness of CoT Monitoring

arXiv · Research · Models

Beware What You Autocomplete: Forensic Attribution of Backdoored Code Completions

arXiv · Research · Models

AI Security

Multi-Agent Firewall Architecture for Privacy Protection of Sensitive Data in Interactions with Language Models

arXiv · Research · AI Security

Prismata: Confining Cross-Site Prompt Injection in Web Agents

arXiv · Research · AI Security

Advisories in this window

  • 27 npm advisories · 26 critical · 1 moderate
  • 20 Packagist advisories · 3 critical · 8 high · 8 moderate · 1 low
  • 9 PyPI advisories · 4 high · 5 moderate
  • 7 Go advisories · 1 high · 6 moderate
  • 4 Hex advisories · 2 high · 1 moderate · 1 low
  • 3 Maven advisories · 2 high · 1 moderate
  • 2 RubyGems advisories · 1 high · 1 moderate
  • 1 Multi-ecosystem advisory · 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.