Every AI agent you wire into your pipeline is a new confused deputy sitting between your issues, your logs, your git tree, and a shell. (Charming, isn't it? ) So when the vendor that put this pattern on the map ships a tool aimed squarely at the pattern's worst failure mode, it is worth clocking.
Source: [Dev.to](https://dev.to/leobaniak/openai-ships-gpt-red-to-automate-prompt-injection-testing-against-ai-agents-od7)