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
METR · August 31, 2026

Update on Security at METR

analysis Agent SecurityModel EvaluationAI Engineering
Why it matters

METR details two external attacks: a fail-open authentication bug in an agent dashboard exposed a public-model API key, and a separate query endpoint could expose unpublished evaluation data. Attackers used the stolen key for credits valued at about $600,000; METR says it found no evidence that sensitive information was accessed. Its response included credential rotation, isolated public infrastructure, deployment review, expanded logging and usage alerts.

My takeaway: Require security review before exposing research apps, test authentication failure paths, and separate public transcript services from private evaluation data. Scope and shorten credential lifetimes, monitor usage even when credits are free, and rehearse revocation and host isolation. Check data classification as well as query authorization before publishing a dataset viewer.
Keep exploring

More curated notes connected through Agent Security and Model Evaluation.

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.