A new benchmark conned every frontier AI agent it tested.

Automated excerpt

Every one of the seven frontier multimodal models tested - including Claude, GPT, Gemini, Kimi, Qwen, MiniMax and GLM variants acting as agents - was vulnerable. Adding multimodal content - a fake package screenshot, a doctored brochure - raised attack success from 19.9% to 29.2% in an ablation covering 86 Level-3 scenarios across seven models.

Selected automatically from source text; not independently written or fact-checked. Read the original for full context.