We benchmarked our prompt-injection detector against OWASP's LLM Top 10

Automated excerpt

We just published our first public benchmark for AgentGuard, the runtime we're building to secure AI agents in production. The honest version: our deterministic (regex) layer alone catches 91. 5% of prompt injection attempts with zero false positives, in under 2ms. Adding a ML layer pushes recall to 98. 1% — but the trade-offs are real: ~450ms latency, and a 33% false-positive rate on benign prompts that were deliberately worded to look like attacks.

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