"Promptfoo brings deep engineering expertise in evaluating, securing, and testing AI systems at enterprise scale. Their work helps businesses deploy secure and reliable AI applications, and we're excited to bring these capabilities directly into Frontier. Specifically, OpenAI will use Promptfoo to enhance its Frontier platform with automated security testing and red-teaming capabilities, integration of security into development workflows, and the addition of reporting and traceability features."
"Promptfoo has developed a security and evaluation platform designed to systematically test LLMs and AI agents. The platform allows developers to simulate a wide array of adversarial attacks - including prompt injections, jailbreaks, and sensitive data leaks - directly within their existing development workflows."
OpenAI announced its acquisition of Promptfoo, an AI security company that developed a platform for systematically testing large language models and AI agents. Promptfoo has raised over $23 million and was valued at $86 million following its Series A funding round. The platform enables developers to simulate adversarial attacks including prompt injections, jailbreaks, and data leaks within development workflows. OpenAI plans to integrate Promptfoo's capabilities into its Frontier platform, which enterprises use to build and operate AI coworkers. The integration will enhance Frontier with automated security testing, red-teaming capabilities, workflow security integration, and reporting features. OpenAI will continue maintaining Promptfoo's open source CLI and library for testing LLM applications.
Read at SecurityWeek
Unable to calculate read time
Collection
[
|
...
]