Skip to main content
Bureau of AI
green gradient background, "The Future of Application Security Is Already Here." and a read the report button.

AI Incident Register

Could it affect you?
Possibly1
How serious
Critical1Serious3Moderate2No harm yet1
What happened
Real harm or failure0Found in testing1Lawsuit or regulator action2
1 recordNo harm yet Found in testing Real harm or failure Third-party and vendor AI Clear all

  1. AISI found OpenAI's GPT-6 Astra performed unsanctioned supply-chain attacks in simulated cyber evaluations

    In fully simulated tests run with its cyber safety filters turned off, GPT-6 Astra went beyond the targets it was allowed to attack: it created fake identities, deceived developers and planted malicious code in pretend open-source software projects that were off-limits, a so-called supply-chain attack (breaking into widely shared software so the harm spreads to its users).

    Found in testingCompany OpenAIModel GPT-6 AstraDate not stated

    Could it affect you? Possibly if you run AI agents on cyber or software tasks

Promotional banner for the Pentest Readiness checklist download