On-Prem Red Team AI — engineering notes from the front line
Deep dives, comparisons and field reports on autonomous red team AI, generative pentesting, deep-packet traffic intelligence, NIS2/DORA, and how to operate them air-gapped.
- Agentic AICredential HarvestingAutonomous Attack Framework
AI Agents Harvested Thousands of Credentials in Under Six Hours
Google's GTIG watched a financially motivated actor use a multi-agent AI framework to build and run a mass credential-harvesting campaign in under six hours — no human in the loop. What it changes for defenders.
8 min read - Magento Zero-DayAdobe CommerceCVE-2026-75650
CVE-2026-75650 StyleSmuggler: Magento Zero-Day RCE Planting Backdoors
CVE-2026-75650: CVSS 10 unauthenticated RCE in Magento and Adobe Commerce, exploited since 4 September to plant a Rust backdoor beaconing as NTP.
10 min read - GPT-6 AstraAI Exploit GenerationChrome Zero-Day
GPT-6 Astra Writes Working Exploits — and CVE-2026-85046 Is the Live Test
OpenAI's GPT-6 Astra crossed the 'Critical' cyber threshold, scoring 100% on ExploitBench. AI exploit generation just collapsed the patch window — CVE-2026-85046 shows why.
8 min read - Kestra RCECVE-2026-49869Authentication Bypass
CVE-2026-49869 Kestra Auth Bypass RCE (CVSS 10, CISA KEV): Fix and Hunt
CVE-2026-49869: a suffix check in Kestra's auth filter makes any /configs path an unauthenticated RCE. CVSS 10, in CISA KEV, exploited for cryptomining.
9 min read - AI-Generated ExploitsOT SecurityPLC Security
AI Ported a Pre-Auth PLC Exploit for $535: Reading Forescout's WAGO Experiment
Forescout used Claude to port a pre-auth RCE exploit (CVE-2021-31886) between WAGO PLC models for $535 in under a day. What AI-lowered exploit cost means for OT defenders who can't patch.
10 min read - Starlette BadHostCVE-2026-48710FastAPI Security
BadHost (CVE-2026-48710): the FastAPI Auth Bypass Now Chained to Ransomware
'BadHost' (CVE-2026-48710) is a one-character Host-header auth bypass in Starlette, the framework under FastAPI, vLLM and LiteLLM — CVSS 6.5, now KEV-listed and chained to ransomware.
9 min read - AI Coding AgentsGitSpawnSupply Chain
GitSpawn: A Malicious Git Config Makes AI Coding Agents Run Attacker Code
GitSpawn: a repo's own .git/config can make Claude Code, Codex, Cursor and other AI coding agents run attacker code outside the sandbox, with no prompt. What to check now.
10 min read - JFrog ArtifactoryCVE-2026-82329Supply Chain
JFrog Artifactory CVE-2026-82329: One Request Away From Admin on Your Build Pipeline
CVE-2026-82329 is a CVSS 9.8 authentication bypass in JFrog Artifactory. A phantom join key lets an unauthenticated attacker forge admin tokens — patched Aug 28, exploited Sep 1.
9 min read - LangflowCVE-2026-0768AI Stack Security
Langflow CVE-2026-0768: One Endpoint Turns Your AI Stack Into an Attacker's Python Shell
CVE-2026-0768 gives unauthenticated attackers root-level Python on exposed Langflow servers — and they are already harvesting OpenAI and AWS keys. Why the AI stack is the soft target.
9 min read