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
AWS Security Blog · August 19, 2026

Propagate user authorization context in AI agents with Amazon Bedrock AgentCore

guide Agent SecurityAI EngineeringAI Compliance
Why it matters

AWS demonstrates three ways to carry user identity through an AgentCore application: STS session tags for DynamoDB authorization, metadata filters for Bedrock Knowledge Bases, and RFC 8693 on-behalf-of exchange for external services. The design keeps enforcement in infrastructure and downstream systems instead of asking the model to filter results.

My takeaway: Validate the user token before agent code runs and propagate a short-lived, audience-bound identity to every tool. Prefer downstream row- or resource-level enforcement over query wording, use separate knowledge bases where metadata filters are not a sufficient boundary, avoid broad service accounts, and log the user, assumed role, scope, and object accessed in one trace.
Keep exploring

More curated notes connected through Agent Security and AI Engineering.

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

OpenAI’s Frontier Governance Framework

OpenAI's 22-page Frontier Governance Framework maps its frontier-model processes to California's Transparency in Frontier AI Act and the EU AI Act's general-purpose AI code. It documents lifecycle risk assessment, cyber-offense and other risk tiers, mitigation and residual-risk decisions, critical-incident handling, security risk management, model reporting, external review, responsibility allocation, and change control.

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.