Fooling AI Agents: Web-Based Indirect Prompt Injection
⚠️ Unit 42 researchers describe web-based indirect prompt injection (IDPI), where adversaries embed hidden or obfuscated instructions in webpages that are later consumed by LLMs and agentic systems. The report catalogs 22 payload engineering techniques, presents a taxonomy of attacker intents from low to critical, and details multiple in-the-wild detections, including the first observed AI ad-review bypass. It emphasizes detection, intent analysis and web-scale defenses to protect automated pipelines.
