Prompt injection gets talked about in abstract terms — "the model was tricked" — but the concrete damage is usually the same: a secret that was sitting in the agent's context gets exfiltrated. To defend against it, it helps to walk through the actual attack chain, step by step. The attack chain...
Source: [Dev.to](https://dev.to/ikkun1222/prompt-injection-and-api-key-exfiltration-what-actually-happens-344m)