AI Red Team Engineering notes, research references, and field notes on AI systems, responsible AI, governance, and compliance.
Global search

Search AI Red Team

Search across the complete knowledge base.

Enter at least two characters to begin.
↑↓ select Enter open Browse the full research archive
OWASP GenAI Security Project · April 15, 2026

FinBot CTF Is Live: A Hands-On Companion to the OWASP GenAI Security Project

tool AI Red TeamingPrompt InjectionAgent Security
Why it matters

OWASP FinBot is a hands-on agentic-security CTF built around a simulated multi-agent financial-services platform with real tool access. Its challenges cover prompt injection, tool misuse, policy bypass, data exfiltration, privilege escalation, remote code execution, shared context, and compromised MCP servers.

My takeaway: Use FinBot as a repeatable lab rather than a one-time puzzle: record the attacker goal, poisoned data path, tool and permission boundary, observable evidence, and successful impact for each challenge. Map findings to OWASP, CWE, and MITRE ATLAS, then convert the exploit path into a control test and regression case for your own agents.
Keep exploring

More curated notes connected through AI Red Teaming and Prompt Injection.

OWASP GenAI Security Project · guide

OWASP Top 10 for Agentic Applications for 2026

OWASP's community guide organizes agentic-system risk into ten categories, including goal hijacking, tool misuse, identity and privilege abuse, memory poisoning, insecure inter-agent communication, cascading failures, and rogue-agent behavior. It provides a shared taxonomy and mitigation starting point rather than a certification checklist or evidence that a deployed system is secure.

Google Cloud Security Blog · tool

Now in preview: Find and fix software vulnerabilities with CodeMender

Google opened a preview of CodeMender, an AI code-security agent delivered through Gemini Enterprise Agent Platform and AI Threat Defense. It is designed to inspect code, identify and validate potentially exploitable defects, and produce targeted fixes, with Google’s specialized Gemini 3.5 Flash Cyber model initially restricted to governments and trusted partners.

NVIDIA AI Red Team · analysis

Mitigating Indirect AGENTS.md Injection Attacks in Agentic Environments

NVIDIA walks through a simulated Go dependency that detects Codex, writes a malicious AGENTS.md, redirects the coding task, and injects instructions intended to conceal the change from pull-request summaries. The post then maps the chain to dependency, configuration-integrity, monitoring, and guardrail controls.