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
Microsoft Security Blog · October 21, 2026

Compromised OAuth applications: hunt for persistence beyond the original app

news Agent SecurityAI Red Teaming
Why it matters

Microsoft’s ARTEX investigation describes abuse of already trusted ConnectWise applications, followed in some tenants by Microsoft Graph activity and credential or privilege changes. Such changes can preserve access after the original app is contained. Successful authentication alone does not prove data access or exfiltration; responders need to correlate sign-ins with subsequent actions.

My takeaway: Find affected applications by application ID and record each tenant’s service-principal ID. Preserve sign-in and audit evidence while containing access. Correlate app-only sign-ins with credential additions, consent grants, owners, privileged roles, and resource access. Investigate unfamiliar sources beyond listed IPs, and verify that remediation removes secondary persistence.
Keep exploring

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

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.

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.

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.