/learn

AI Agent Security Guides

In-depth, practical guides to the attack classes and defenses shaping the AI agent security landscape. Written from the perspective of a red team, not a product marketer.

Reference

AI Bug Bounty Programs in 2026: Active List with Payouts

Every active AI bug bounty program in 2026: OpenAI ($100K max), Anthropic, Google, Microsoft, xAI/Grok, Cohere, Mozilla 0din, Gray Swan Arena. Verified scopes, payout ranges, and application links.

8 min read·22 sections
![img](https://evil...)
Attack Guide

Data Exfiltration via Markdown Images: The Quiet AI Vulnerability

Markdown image rendering is the most underrated data exfiltration channel in AI products. A working model of how it leaks system prompts, conversation history, and tool output — and the four defensive patterns that actually close the channel.

14 min read·13 sections
Methodology

How to Find Your First LLM Bug Bounty

A practical guide to finding your first payable vulnerability in an AI-powered application. Covers which programs accept LLM findings, what to look for, how to demonstrate impact, and the common mistakes that get reports closed.

7 min read·12 sections
Attack Guide

Indirect Prompt Injection: The Attack That Doesn't Need the Keyboard

A complete guide to indirect prompt injection in 2026: the attack where the adversary never types a word to the AI. How it works, the five injection channels in production systems, real-world incidents, and the architectural defenses that actually hold.

15 min read·20 sections
!!!MEMORY
Attack Guide

Memory Poisoning: How 'Remember This' Becomes the Side Door

Memory features in AI agents bolt a retrieval layer onto a language model and ship it as a product. The attack surface they create is more dangerous than RAG, more permanent than session injection, and almost completely undefended at the layer that matters.

16 min read·22 sections
Attack Guide

Prompt Injection: A Complete Guide for 2026

Everything you need to understand prompt injection as an AI developer or security engineer: the attack classes, why they work, why traditional defenses fail, and how to actually test for them.

10 min read·24 sections
Methodology

Red-Teaming Agentic AI: A Practitioner's Checklist

A structured methodology for security-testing AI agents with tools, memory, and multi-step reasoning. Covers the five phases of an agent red-team engagement, specific attack techniques per phase, and the artifacts you should deliver.

8 min read·10 sections
Defense Guide

Securing RAG Systems: A Practical Guide

Retrieval-Augmented Generation is the most common architecture for production AI applications. It's also one of the easiest to poison. This guide covers the five attack surfaces unique to RAG, with concrete defensive patterns for each.

8 min read·16 sections
Attack Guide

System Prompt Extraction: Techniques and Defenses

A complete reference on system prompt extraction attacks: direct, indirect, and side-channel techniques, why the obvious defenses fail, and the four-layer defense stack that actually works in production.

12 min read·17 sections
Defense Guide

The AI Agent Threat Model: A Practitioner's Guide

How to build a threat model for AI agents with tools, memory, and multi-step reasoning. Covers trust boundaries, data flows, attack surfaces, and the five questions every agent threat model must answer.

7 min read·16 sections
10
Reference

The OWASP Top 10 for LLM Applications, Annotated (2026 Edition)

A practitioner's walk through every item in the OWASP Top 10 for LLM Applications — what each one actually means, how attackers exploit it in the wild, why the standard mitigations fall short, and what to do instead.

16 min read·12 sections
$
Reference

The State of LLM Bug Bounties in 2026

A practitioner's guide to where LLM bug bounties actually pay in 2026 — program-by-program scope comparison, typical payouts, which classes of AI bugs get rewarded versus closed as 'known limitation,' and how to pick a scope that fits how you hunt.

12 min read·15 sections
Attack Guide

Tool Abuse in AI Agents: The Next SQL Injection

When AI agents have tools, prompt injection becomes catastrophic. This guide covers the taxonomy of tool abuse attacks, real-world exploitation patterns, and defensive architectures that actually constrain what an agent can do.

10 min read·27 sections