Gemini 2.5
Google DeepMind — Gemini
rich detail 9 method fields published
Evaluation
External indirect prompt injection susceptibility evaluation
External evaluation of patterns of susceptibility to indirect prompt injection: vulnerabilities in function calls, asymmetries across security measures, and domain-dependent hijack rates
How it was run
Open a release to see the setup, scoring, and other details that the lab published. Only fields the lab actually disclosed are shown.