Can open-source prompt-injection detectors catch realistic AI agent attacks?

Automated excerpt

Can open-source prompt-injection detectors catch realistic AI agent attacks? firewall actually sees them. None catches most attacks without also blocking AgentDojo tool output. Can a detector, reading the text an agent sees, flag an injection attack without wrongly flagging benign tool output? 🤖 Run a live agent.

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