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 15 August 2025 · Retrospective · Covers 14 August 2025 00:00 to 15 August 2025 00:00 UTC

Read on the web

Top developments

Case Study: How LFX Insights and OSPS Baseline Validated GUAC’s Security in Under an Hour

OpenSSF · Research · SCA

Leak: OpenAI's browser will use ChatGPT Agent to control the browser

BleepingComputer · Incident

LLM Coding Integrity Breach

Schneier on Security · Incident

SAST

MCP-Guard: A Multi-Stage Defense-in-Depth Framework for Securing Model Context Protocol in Agentic AI

arXiv · Research · AI Security, Models, SAST

Data and Context Matter: Towards Generalizing AI-based Software Vulnerability Detection

arXiv · Research · SAST

Enhancing GraphQL Security by Detecting Malicious Queries Using Large Language Models, Sentence Transformers, and Convolutional Neural Networks

arXiv · Research · SAST

Agentic SDLC

Google Jules: Vulnerable to Multiple Data Exfiltration Issues

Embrace The Red · Analysis · Agentic SDLC

Remediation

Microsoft fixes Windows Server bug causing cluster, VM issues

BleepingComputer · Analysis · Remediation

Trust

CoSAI at Cyber EUnnovate 2025

CoSAI · Analysis · Trust

Announcing Kernel-Independent FIPS for Java

Chainguard · Analysis · Trust

Models

Benchmark Dataset Generation and Evaluation for Excel Formula Repair with LLMs

arXiv · Research · Models

Jailbreaking Commercial Black-Box LLMs with Explicitly Harmful Prompts

arXiv · Research · Models

A Vision-Language Pre-training Model-Guided Approach for Mitigating Backdoor Attacks in Federated Learning

arXiv · Research · Models

AI Security

Jules Zombie Agent: From Prompt Injection to Remote Control

Embrace The Red · Analysis · AI Security

Advisories in this window

  • 4 PyPI advisories · 4 moderate
  • 3 Go advisories · 3 moderate
  • 2 crates.io advisories · 1 high · 1 moderate
  • 1 npm advisory · 1 critical
  • 1 RubyGems advisory · 1 critical

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.