New Archestra's OpenAPPA Saturates Two Major Security Benchmarks with a 0% Attack Success Rate
Archestra has launched OpenAPPA, an open-source security engine designed to prevent data exfiltration from prompt injection and model hallucinations.
OpenAPPA operates outside the agent's execution loop, utilizing deterministic rules based on data sources, trust levels, and authorities. In testing against Bench-Corp and AgentThreatBench, the engine achieved a 0% attack success rate, outperforming existing benchmarks like Claude Code and Microsoft FIDES.