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
OWASP GenAI Security Project · September 2, 2026

OWASP updates LLM Top 10 and adds Agent Control Standard

news AI Red TeamingPrompt InjectionAgent SecurityAI Compliance
Why it matters

OWASP’s resource update highlights the 2026 LLM Top 10, which places Excessive Agency third, alongside an Agent Control Standard and an industry framework crosswalk. ACS defines middleware hooks for portable runtime policies. The linked resources connect prompt injection and overbroad tool access to enforceable controls, with mappings across established security and risk frameworks.

My takeaway: Use the updated risk scenarios to review tool permissions and action boundaries, then map each relevant risk to an implemented control and test evidence. Evaluate ACS hooks against the agent frameworks you actually run. A framework mapping documents coverage; verify separately that the runtime blocks unauthorized actions and records the decision.
Keep exploring

More curated notes connected through AI Red Teaming and Prompt Injection.

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.