~/f4n6 $ adversetrace --mode blog --sovereign true
// latest

Three companies, one OAuth token, and the case for sovereign AI

On 19 April 2026, Vercel disclosed a security incident. Within 48 hours, the public attack chain had resolved into something more interesting than the initial "cloud platform breach" framing: an infostealer infection

read post →
// field notes

Things I build & break

AI

GLM-4.7-Flash on Nvidia GB10

So I have gotten into running my own local llm for privacy reasons, and like to use it to assist with incident response tasks and collecting

31 Mar 2026 · 9 min read read →
// security feed

Curated, attributed, dated

full feed →
21 Jul 2026 f4n6
AI agents are still logging in as humans

1. Executive summary Okta's Enterprise AI Index, drawing on anonymised sign-on data from over 20,000 organisations (June 2022–June 2026)

→
21 Jul 2026 f4n6
Cursor, Codex, Gemini CLI, Antigravity hit by sandbox escapes

1. Executive summary Pillar Security researchers demonstrated sandbox escapes across four widely used AI coding agents — Cursor, OpenAI Codex CLI, Google Gemini CLI, and

→
21 Jul 2026 f4n6
New ENCFORGE Ransomware Targets AI Model Files in Langflow RCE Attack

1. Executive summary JADEPUFFER, an actor attributed by Sysdig to an autonomous LLM-driven AI agent (no MITRE ATT&CK profile exists for

→
21 Jul 2026 f4n6
OVH reveals semi-secret plan to fix critical Januscape hypervisor bug with mass reboots – and an Australian crash-test dummy

1. Executive summary CVE-2026-53359 ("Januscape") is a HIGH-severity (CVSS 8.8) use-after-free vulnerability in the Linux KVM

→
21 Jul 2026 f4n6
Critical ServiceNow AI Platform Flaw Exploited for Unauthenticated Code Execution

1. Executive summary A critical code injection vulnerability (CVE-2026-6875, CVSS 9.5) in the ServiceNow AI Platform is being actively exploited in

→
view full security feed →