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 29 August 2025 · Retrospective · Covers 28 August 2025 00:00 to 29 August 2025 00:00 UTC

Read on the web

Top developments

Malware devs abuse Anthropic’s Claude AI to build ransomware

BleepingComputer · Incident · Agentic SDLC

Researchers Find VS Code Flaw Allowing Attackers to Republish Deleted Extensions Under Same Names

The Hacker News · Research · SCA

Agentic AI coding assistant helped attacker breach, extort 17 distinct organizations

Help Net Security · Incident · Agentic SDLC, AI Security

SAST

AVIATOR: Towards AI-Agentic Vulnerability Injection Workflow for High-Fidelity, Large-Scale Code Security Dataset

arXiv · Research · AI Security, SAST

Cycuity Radix-ST identifies security weaknesses earlier in chip design

Help Net Security · Analysis · SAST

SCA

Unpacking Passkeys Pwned: Possibly the most specious research in decades

Ars Technica: Security · Analysis · SCA

DAST

Multi-Agent Penetration Testing AI for the Web

arXiv · Research · Agentic SDLC, DAST

Agentic SDLC

Windsurf MCP Integration: Missing Security Controls Put Users at Risk

Embrace The Red · Analysis · Agentic SDLC, AI Security

How we accelerated Secret Protection engineering with Copilot

GitHub · Analysis · Agentic SDLC, Remediation

Remediation

High-severity vulnerability in Passwordstate credential manager. Patch now.

Ars Technica: Security · Analysis · Remediation

Trust

Poison Once, Refuse Forever: Weaponizing Alignment for Injecting Bias in LLMs

arXiv · Research · Models, Trust

Models

Misleading Large Language Models used (or misused) in Scientific Peer-Reviewing via Hidden Prompt-Injection Attacks

arXiv · Research · AI Security, Models

JADES: A Universal Framework for Jailbreak Assessment via Decompositional Scoring

arXiv · Research · Models

MindGuard: Intrinsic Decision Inspection for Securing LLM Agents Against Metadata Poisoning

arXiv · Research · AI Security, Models

AI Security

PromptSleuth: Detecting Prompt Injection via Semantic Intent Invariance

arXiv · Research · AI Security

Advisories in this window

  • 7 Go advisories · 1 critical · 2 high · 3 moderate · 1 low
  • 4 Packagist advisories · 4 moderate
  • 2 Maven advisories · 1 critical · 1 moderate
  • 1 npm advisory · 1 high
  • 1 NuGet advisory · 1 moderate
  • 1 GitHub Actions 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.