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
NVIDIA AI Red Team · July 31, 2025

Securing Agentic AI: How Semantic Prompt Injections Bypass AI Guardrails

analysis AI Red TeamingAgent SecurityPrompt Injection
Why it matters

NVIDIA's AI Red Team demonstrates multimodal prompt injections encoded as symbolic image sequences and rebus puzzles rather than literal text. In the examples, models interpret visual semantics as code or file commands, including reading and deleting files, showing why text keyword filters and OCR-only inspection do not cover the full input surface of a tool-enabled multimodal system.

My takeaway: Extend prompt-injection testing to images, audio, diagrams, emojis, and combinations whose meaning only appears after model interpretation. Inspect the semantic intent of outputs, but keep the decisive controls outside the model: authorize every tool call, constrain file and network access, require confirmation for destructive actions, and retain traces for regression testing.
Keep exploring

More curated notes connected through AI Red Teaming and Agent Security.

OpenAI News · framework

Pacing model development in an era of cyber-critical capabilities

OpenAI says preliminary evidence that Astra may meet its Critical cybersecurity threshold led it to pause frontier reinforcement-learning work for two weeks and keep its largest planned run on hold. New safeguards include stronger workload and network isolation, continuous boundary testing, token-level monitoring that escalates suspicious tool activity, and broader alignment checks for deception, reward hacking, and unauthorized access.

OpenAI News · framework

A blueprint for democratic governance of frontier AI

OpenAI proposes a three-part U.S. frontier-AI governance model: harmonize emerging state safety laws into a federal baseline, strengthen CAISI as an evaluation and standards institution, and coordinate a broader resilience program. Proposed controls include severe-risk evaluations, transparency reports, independent audits, safety-incident reporting, model-weight security, whistleblower protection, and periodic technical assessments.

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.