Jun 30, 2026
•
5 min read
A closer look at custom-code guardrail sandbox-escape (CVE–2026-40217) activity in the wild
6 min read
A closer look at api_base SSRF (CVE-2024-6587) activity in the wild, and its nested variant
Inside mass discovery and model-probing reconnaissance campaigns that are mapping LLM backend servers in the wild
7 min read
Threat actors attempting to hijack Ollama & LiteLLM endpoints to run pentesting agents, tools and web reverse-engineering
What we can learn from observing real attacks, made by real adversaries
Jun 4, 2026
10 min read
The Latent Undertow beneath fluent LLM behavior — and how to fish your activation probe out of it.
Mar 12, 2026
How understanding the training algorithms used in machine learning models may allow attacker to bypass them entirely
Security research
Mar 3, 2026
26 min read
One Calendar Invite. Your Entire Vault. Zero Clicks.
25 min read
Local Files Are No Longer Safe.
Feb 18, 2026
22 min read
How Untrusted Content Triggered 1,000+ Agent Endpoints Worldwide and Exposed Moltbook’s Faulty Design
11 min read
Beyond input & output filtering and how well does it generalize to your out-of-distribution production data?
Feb 11, 2026
13 min read
A deeper look into an agentic browser's inner workings
