NewAgentic Threat Groups: From Prompts to Autonomous Intrusions

Security,decoded.

Field notes on AI security, cloud architecture, Zero Trust and the vulnerabilities that matter. Written by William OGOU for builders and defenders.

Articles
200
Topics
833
Categories
10

Popular topics

TopicsBrowse by topic

Latest

Fresh from the lab

The newest field notes on AI security, cloud and the vulnerabilities that matter.

View all

Topic atlas

Find your domain

10 categories, one map. Each bar shows a category's share of all 200 articles.

All topics

AI Security

Securing LLMs, agents and MCP: from prompt injection to AI-era supply chains.

67articles

34%

Cybersecurity

Threats, trends and strategy for security leaders and practitioners.

37articles

19%

Vulnerabilities

Critical flaws, active exploitation and the playbooks to respond.

27articles

14%

Cloud Security

Hardening GCP, Azure and AWS: identity, data and network guardrails.

26articles

13%

Zero Trust

Never trust, always verify: identity-first architectures, SASE and ZTNA.

7articles

4%

Network Security

Firewalls, edge and the network layer of defence in depth.

1article

<1%

Every topic

Browse the full tag index, from AI agents to zero-days.

833tags

Archive

From the archive

8 more recent reads, newest first. The full library has 200 articles.

  1. GitHub Package Firewall: Install-Time Security for AI Agents and Pipelines

    GitHub Package Firewall brings install-time npm policy gates, SLSA attestation checks, and version cooldowns to AI coding agents and CI/CD runners.

    Supply Chain
  2. Node.js Brotli RCE (CVE-2026-111497): Patch Guide

    Node.js CVE-2026-111497 exposes Brotli decoding to potential RCE. Check affected versions, fetch() exposure, WAF limits, and the October 2026 patch checklist.

    Vulnerability
  3. PHP2Shell (CVE-2026-109618 & CVE-2026-109619): Critical PHP RCE Patch Guide

    PHP2Shell (CVE-2026-109618 & CVE-2026-109619) exposes 70% of the web to unauthenticated PHP RCE and memory leaks. Check fixed versions, IOCs, and mitigations.

    Vulnerability
  4. Google Cloud VPC-SC Updates: Folders, PSC Endpoints & Remediation

    Google Cloud VPC Service Controls now supports folder-level perimeters, folder and organization rules, PSC endpoints, service patterns, and guided violation remediation. Here are the technical details and YAML configs.

    Cloud Security
  5. Self-Replicating AI Without Datacenters: Anthropic IoT Worm Research

    Anthropic's Frontier Red Team tested whether small open-weight AI models can self-replicate across cheap IoT devices without datacenter GPUs. See what worked, what was simplified, and how defenders can keep R0 below 1.

    AI Security
  6. AI-Era CVE Trends: Discovery and Exploitation

    Google's GTIG data shows CVE disclosures doubled in 2026, n-day exploitation is accelerating, and AI stacks are now targets. See what it means and how to respond.

    Vulnerability
  7. Cloudflare Agentic SOC: Managed Defense AI Harness Explained

    Cloudflare Managed Defense is testing an evidence-grounded SOC harness with Clef and specialist AI agents. Learn how it works, what stays human-controlled, who can access the beta, and what agentic SOCs need next.

    AI Security
  8. Cloudflare CA: Free Post-Quantum Certificates with MTCs in 2027

    Cloudflare plans free MTC certificates from 2027. See its new CA roadmap and current PQC services: Automatic Key Exchange, ML-DSA origin authentication, Tunnel, and certificate monitoring.

    Cybersecurity
Portrait of William OGOU

Meet the author

William OGOU

Google Cloud & AI Security Architect | CISSP, OSCP

Cybersecurity specialist and cloud architect building privacy-first AI tools. Here he writes about AI and LLM security, DevSecOps, cloud security on Google Cloud and security architecture.

  • AI Security
  • LLM Security
  • DevSecOps
  • Cloud Security
  • Google Cloud
  • Security Architecture