An independent knowledge resource for offensive AI security and AI engineering. Daily intelligence, in-depth guides, hands-on courses, and original research on how LLMs, agents, and AI-connected systems actually fail.
SharePoint ToolShell v2 chain (CVE-2026-56164, CVE-2026-58644) and AD FS zero-day CVE-2026-56155 drive Microsoft's record 622-CVE Patch Tuesday; Langflow IDOR CVE-2026-55255 (CVSS 9.9) becomes first AI-agent infra in CISA KEV; Anubis ransomware halts Coca-Cola Fairlife production and threatens 1TB leak.
Read the latest CTI briefMCP finalizes its 2026-07-28 stateless spec today (beta SDKs shipping: Python 2.0.0b1, TypeScript v2, Go v1.7.0-pre.1, C# 2.0.0-preview.1), Claude Code 2.1.219 makes Opus 5 the default and unlocks depth-3 nested subagents, and Anthropic publishes its formal open-weights position.
Read the latest AI brief196 intelligence briefs, published every morning. Agent-drafted, verified by a human before they ship.
Traditional scanners fuzz bytes. AI vulnerabilities live in meaning. Prompt injection is not a malformed HTTP request. It is a sentence that sounds helpful but changes the model's behavior. The only thing that can probe meaning at scale is another AI.
Same prompt, different response every time. Static test suites are useless. Evaluating an AI system means running hundreds of variations and measuring success probabilistically, not checking a single pass or fail.
The most dangerous AI attacks are multi-turn conversations that gradually shift context, build trust, and bypass guardrails that catch single-prompt attempts. Only AI maintains that strategic state.
A jailbroken chatbot says something inappropriate. A jailbroken agent with database access exfiltrates data, modifies records, and executes code. The blast radius is orders of magnitude larger.
Everything here is free to read: daily intelligence, in-depth guides, a structured course, and original research on AI and agentic security.
A threat intelligence brief and an AI security brief, published every morning. Agent-drafted, human-verified, every claim sourced.
In-depth pillar guides on MCP security, prompt injection testing, agentic AI red teaming, and AI agent security, plus a 30-lesson structured course from foundations through advanced.
Long-form articles on AI and agentic security, including a build-oriented series that walks through constructing an agentic red team from scratch.
A curated hub of AI education video content and courses from across the field, organized so the good material is easy to find.
The word agent gets used for a chatbot with a system prompt, a script in a loop, and a system that plans and acts on its own. Three different animals. Only one can hurt you. A red teamer's guide to what an AI agent actually is and what agentic really means.
The autonomy that lets an agent clear your overnight queue is the same autonomy that lets one poisoned document turn it against you. One property, two sides. Why the more agentic the system, the further a single injection travels.
You will never make the model deterministic. So stop trying. You make the system around it deterministic, shrink the part that needs judgment to almost nothing, and put a fence around what's left. Here is how that actually works.
New threat intelligence every morning, in-depth guides on the attack surfaces that matter, and a structured course that runs from foundations to advanced. All of it free to read.