Co-RE

Co-RE refers to the Collaborative Research Establishment, a governance framework that enables multiple organizations to jointly develop and oversee AI systems while maintaining compliance standards across institutional boundaries. This matters for enterprises because it addresses the complexity of shared AI development where responsibility, liability, and regulatory compliance must be clearly distributed among partners. Organizations using Co-RE can better manage risks in collaborative AI projects while ensuring each party understands its obligations under data protection, algorithmic accountability, and emerging AI regulations.

1 item

ResearchGlobal2026-09-16

Multimodal Prompt Injection Exposes Structural Gap in Agent Red-Teaming

Co-RE has published a catalog of attack techniques targeting AI agents across text, image, document, audio, and multimodal input channels. The research documents zero-click and hidden injection paths that can cause agents to leak data or take unauthorized actions. Most enterprise red-teaming programs test only direct text-based jailbreaks and do not cover these broader attack surfaces.

prompt injection multimodal red teaming agentic AI agent security Co-RE