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 7 August 2026 · Retrospective · Covers 6 August 2026 00:00 to 7 August 2026 00:00 UTC

Read on the web

Top developments

Cisco Patches 12 SD-WAN and IOS XE Flaws, Including Three 9.9 CVSS Score Bugs

The Hacker News · Advisory · Remediation

Swiss government SharePoint breach compromised 200 accounts

BleepingComputer · Incident

Meta AI model hacked a company during misconfigured cyber test

BleepingComputer · Incident

SAST

RustGo: Fairly Directed Greybox Fuzzing for Enforcing Rust Memory Safety

arXiv · Research · DAST, SAST

Agent-Based Test Assertion Generation via Diverse Perspective Aggregation

arXiv · Research · SAST

SCA

How we took malware advisories beyond npm

GitHub · Analysis · SCA

DAST

From Documentation to Zero-day Vulnerabilities: LLM-Driven Fuzzing of JavaScript Engines in PDF Readers

arXiv · Research · DAST

ZAP Updates - July 2026

ZAP (Checkmarx) · Release · DAST

Agentic SDLC

The Vulnerability With No CVE: Managing Persistent Gaps Between Mandate and Authority in AI Coding Agents

arXiv · Research · Agentic SDLC, AI Security

Reasoning from Traces: Divergence-Guided Agentic Repair of WebAssembly Discrepancies

arXiv · Research · Agentic SDLC

Remediation

CyberForge: Verified Vulnerability Injection at Repository Level for Cybersecurity Agent Training

arXiv · Research · Remediation

Trust

How AI Exposed a Browser Security Gap that Enterprises Cannot Ignore

BleepingComputer · Analysis · Trust

Models

StepJack: Benchmarking Computer-Use Agent Safety Against Multi-Step Indirect Prompt Injection

arXiv · Research · AI Security, Models

Algebraic Cryptanalytic Extraction on Hard-Label Neural Networks

arXiv · Research · Models

Breaking Customized LLMs for Coding: Automated Red Teaming for Instruction Backdoor Attacks

arXiv · Research · AI Security, Models

AI Security

AI Recommendation Poisoning: How "Ask AI" Buttons Silently Alter LLM Memory

The Hacker News · Analysis · AI Security

Hardware Keystores for AI Agent Signing Workflows: A Zero-Trust MCP Enforcement Architecture

arXiv · Research · AI Security

Hijacking Robots with a Piece of Paper: A Systematic Study of Physical Prompt Injection in VLM-Controlled Robots

arXiv · Research · AI Security

Advisories in this window

  • 84 npm advisories · 75 critical · 2 high · 6 moderate · 1 low
  • 26 Packagist advisories · 9 high · 14 moderate · 3 low
  • 8 Go advisories · 1 critical · 3 high · 3 moderate · 1 low
  • 6 PyPI advisories · 3 critical · 3 moderate
  • 1 Maven 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.