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, Wednesday 12 August 2026 · Retrospective · Covers 11 August 2026 00:00 to 12 August 2026 00:00 UTC

Read on the web

Top developments

Microsoft August 2026 Patch Tuesday fixes 400 flaws, 3 zero-days

BleepingComputer · Advisory · Remediation

Cisco warns of ASA and FTD VPN flaw exploited to crash devices

BleepingComputer · Incident

CVE-2026-20349: Cisco Secure Firewall Adaptive Security Appliance (ASA) and Secure Firewall Threat Defense (FTD) Heap Inspection Vulnerability added to CISA's Known Exploited Vulnerabilities catalog

CISA · Advisory

SCA

Agentic Configuration Management (ACM): A Reference Configuration Model for Governed Agentic Systems

arXiv · Research · SCA, Trust

Trigger the Straggler: Load Hijack on Mixture-of-Experts LLMs

arXiv · Research · SCA

Agentic SDLC

On Understanding, Identifying, and Mitigating Vulnerabilities in Agentic Large Language Models

arXiv · Research · Agentic SDLC, AI Security, Models

13 million tool calls: auditing every AI coding agent action with Elastic Agent

Elastic · Analysis · Agentic SDLC

Malicious MCP Servers Can Split Instructions to Make AI Coding Agents Exfiltrate Secrets

The Hacker News · Analysis · Agentic SDLC, AI Security

Remediation

Microsoft Plugs Nearly 400 Security Holes

Krebs on Security · Analysis · Remediation

Windows 11 KB5121003 & KB5120240 cumulative updates released

BleepingComputer · Analysis · Remediation

Trust

EU AI Act: risk tiers, timeline, and compliance requirements

Mend.io · Standard / policy · Trust

Models

Defending against Model Extraction for GNNs with Model Reprogramming

arXiv · Research · Models

An Empirical Study of Output-to-Input Loops for Black-Box Backdoor Detection in Fine-Tuned Open-Weight LLMs

arXiv · Research · Models

Backdoor Decontamination Dynamics in LLM Agents

arXiv · Research · Models

AI Security

The Next Challenge for Agentic Cybersecurity: A Realistic, Contamination-Free Reverse Engineering Benchmark

arXiv · Research · AI Security

When Agents Talk: Honeytokens under Shared Memory

arXiv · Research · AI Security

A Gateway Architecture for Enterprise MCP Authentication: Unifying Heterogeneous Auth, Identity Delegation, and the User / Non-User Persona Problem

arXiv · Research · AI Security

Advisories in this window

  • 45 npm advisories · 44 critical · 1 high
  • 9 NuGet advisories · 6 high · 3 moderate
  • 8 PyPI advisories · 8 critical
  • 1 Go 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.