OpenAI to Acquire Promptfoo
OpenAI announced the acquisition of Promptfoo, an AI security platform focused on identifying and remediating vulnerabilities in AI systems during development. The acquisition signals OpenAI's intent to deepen its enterprise security capabilities. Promptfoo has been widely used by developers to red-team and evaluate LLM applications for safety and reliability issues.
Related guides (4)
Related events (8)
promptfoo: open-source LLM testing and red-teaming framework trending on GitHub
promptfoo is a TypeScript-based open-source tool for testing prompts, agents, and RAG pipelines, with built-in red-teaming and vulnerability scanning capabilities. It supports declarative configs with CLI and CI/CD integration and benchmarks across major models including GPT, Claude, Gemini, and DeepSeek. The project has accumulated 22,323 stars with 46 added today, and claims usage by OpenAI and Anthropic.
Understanding prompt injections: a frontier security challenge
OpenAI has published a blog post addressing prompt injection attacks as a key security challenge for AI systems. The post covers how these attacks work and outlines OpenAI's multi-pronged approach including research, model training improvements, and safeguard development. This signals OpenAI's formal positioning on agentic security threats as their models are increasingly deployed in tool-using and autonomous contexts.
OpenAI Launches Bug Bounty Program
OpenAI announced a formal bug bounty program to crowdsource security vulnerability discovery across its products and services. The initiative is framed as part of OpenAI's broader commitment to building secure and trustworthy AI systems. Researchers who find and responsibly disclose vulnerabilities will be eligible for rewards.
Introducing OpenAI Frontier
OpenAI has launched OpenAI Frontier, an enterprise platform designed for building, deploying, and managing AI agents. The platform provides shared context, onboarding workflows, permissions management, and governance tooling. This positions OpenAI more directly in the enterprise AI infrastructure and agent orchestration market.
OpenAI Cybersecurity Grant Program
OpenAI announced a grant program aimed at developing AI-powered cybersecurity capabilities for defenders. The initiative provides funding and support to researchers and organizations working on defensive cybersecurity applications of AI. This represents OpenAI's effort to direct AI capabilities toward security defense rather than offense.
OpenAI Launches Preparedness Team and Challenge for Catastrophic Risk
OpenAI announced the formation of a dedicated Preparedness team focused on evaluating and mitigating catastrophic risks from highly capable AI systems. The initiative includes a challenge to solicit external input on frontier risk scenarios. This represents a formal organizational commitment to tracking and preparing for severe AI safety risks beyond existing red-teaming efforts.
Accelerating the Cyber Defense Ecosystem with GPT-5.4-Cyber and $10M API Grants
OpenAI is launching a Trusted Access for Cyber program, partnering with leading security firms and enterprises to deploy GPT-5.4-Cyber, a specialized model for cybersecurity applications. The initiative includes $10M in API grants to support global cyber defense efforts. This represents OpenAI's formal entry into the enterprise cybersecurity AI market with a purpose-built model variant.
OpenAI Launches Rosalind Biodefense Program for Government and Vetted Developer Access
OpenAI has launched Rosalind Biodefense, a program expanding trusted access to GPT-Rosalind for vetted developers and U.S. government partners. The initiative targets biodefense, public health, and pandemic preparedness applications. This represents a structured deployment pathway for frontier AI in high-stakes biosecurity contexts.