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 · October 6, 2026

Agent log viewers must treat model output as untrusted content

analysis Agent SecurityModel EvaluationAI Red Teaming
Why it matters

METR demonstrated a stored cross-site scripting weakness in an isolated staging copy of the Inspect evaluation viewer. A model-produced payload could alter the reviewer’s displayed transcript and intercept a download, while leaving the underlying database log unchanged. The report does not describe observed exploitation during evaluations. It documents the initial June fix and later hardening that supports plain-text viewing of untrusted content. The failure mode is a monitoring interface executing material supplied by the system it is meant to inspect.

My takeaway: Use a viewer build containing the relevant fixes, disable rich rendering for untrusted traces, and test both display and export against a separately retained canonical log. Keep monitoring credentials and writable storage outside the evaluated agent’s permissions.
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.