All news

OpenAI brings in Hacktron to find vulnerabilities in connections with third-party services

Prepared by Sintelligent with the help of SI. Published in SI: . Updated: .

Protecting SI agents increasingly depends on testing the entire chain of connected services and permissions, not just the behavior of an individual model.

According to OpenAI's description, as relayed by Unite.AI, company engineers and Hacktron researchers will jointly select priority areas for testing, focusing on weaknesses that arise when applications, identity systems and infrastructure are connected. Hacktron will receive expanded access to frontier models through the Daybreak Red program for authorized vulnerability discovery and security testing. The companies have previously interacted through OpenAI's vulnerability bounty program.

History

OpenAI strengthens internal security

3 events
  1. OpenAI brings in Hacktron to find vulnerabilities in connections with third-party servicesOpen now
  2. OpenAI employees warned management for years about weak protection for research
  3. OpenAI to bring Cathedral into a new security review and raise vulnerability rewards