I tested ChatGPT-6 vs Claude Opus 5.5 with 5 everyday prompts — it wasn’t even close

GitHub – rudratoshs/buried-injections: πŸ›‘οΈ Regex catches 0%, Meta's Prompt Guard 2 catches 1% of 629 realistic AgentDojo injection attacks when they're buried in tool output. Reproducible benchmark. Β· GitHub