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
The Hacker News AI Security · September 2, 2026

AI-assisted PLC exploit port shows capability and physical-system limits

analysis AI Red TeamingModel EvaluationAgent Security
Why it matters

Forescout used Claude Code, a known exploit, firmware and live hardware to port CVE-2021-31886 between WAGO PLC models. Working code execution required repeated researcher guidance; the final development session lasted over eight hours and used $535.74 in API credits. A later attempt to build a command-and-control implant permanently damaged the PLC, illustrating the operational consequences of authorized agents making unsafe changes.

My takeaway: Assess OT exposure by reachability and process impact, and validate AI-generated findings with specialist review. Run experiments on isolated test hardware with recovery plans and explicit limits on device writes. Track human effort, failed attempts and equipment damage alongside exploit success when comparing agent capability or claimed automation gains.
Keep exploring

More curated notes connected through AI Red Teaming 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.