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
Wiz AI Security · October 30, 2026

Stolen AI credentials: detect quiet validation before bulk inference abuse

analysis Agent SecurityAI Red Teaming
Why it matters

Wiz describes two cases in which credentials associated with a compromised vendor were quietly checked before larger Bedrock workloads appeared. One key initially rejected global inference profiles, but abuse resumed after the actor found permitted regional profiles. The observations support monitoring the sequence from key validation to quota probing and heavy use; reseller overlap does not establish who performed the original compromise.

My takeaway: After a vendor credential exposure, revoke affected keys and examine early low-volume inference from unfamiliar sources, model discovery and quota enumeration. Restrict allowed models, regions and inference profiles to business needs, and monitor usage and spend. Test alerts against both slow validation and sudden bursts. Regional restrictions can limit some requests but do not contain a stolen key that retains useful permissions.
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.