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
OpenAI News · February 13, 2026

Lockdown Mode illustrates reducing prompt-injection risk by removing network paths

analysis Prompt InjectionAgent Security
Why it matters

OpenAI’s February 2026 announcement describes Lockdown Mode as a set of deterministic restrictions on features that can expose conversation data to external systems. The article’s June update expands availability and lists additional restricted capabilities. Its architectural lesson is to reduce exfiltration opportunities by disabling or constraining live network access and connected tools. Workspace administrators can retain selected app actions, so the effective boundary depends on configuration. Elevated Risk labels explain tradeoffs but do not themselves enforce a restriction, and the article supplies no comprehensive attack-success evaluation.

My takeaway: Inventory the external actions still available under a restricted configuration and test them with synthetic sensitive data. Separate enforced tool restrictions from warning labels, and review any app exceptions as part of the boundary.
Keep exploring

More curated notes connected through Prompt Injection and Agent Security.

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

Frontier training safety cases: connect evidence to enforced pause and rollback controls

OpenAI proposes training-run safety cases combining alignment evaluations, containment and monitoring with explicit operational ownership. Concrete measures include immutable transcripts, held-out incident tests, checks for evaluation gaming, response deadlines and fail-closed monitoring. Independent internal challenge, leadership vetoes and tracking downstream uses support stopping a run and reversing affected work. The article describes recommendations still being implemented, rather than audited proof that every safeguard already operates or that residual risk has been eliminated.

OECD.AI Wonk · guide

A five-step roadmap to closing the AI evaluation gap

The roadmap addresses evaluation results that overstate real-world performance or fail to transfer across deployment contexts. Its five steps balance standardized and local tests, evaluate throughout the lifecycle, build qualified assurance and communication capacity, tailor tests to each value-chain actor and technology, and use a coordinated, trusted process for updating methods.