Agents attacking other agents were observed in the wild and more to come in the wake of OpenClaw.
RAXE just published a threat intelligence report where they analyzed 38 production AI agent deployments.
Highlights:
- 74,636 agent interactions analyzed
- Inter-Agent Attacks emerged as a distinct category (3.4%) where agents send poisoned messages to other agents, exploit trust relationships, and attempt recursive attack propagation
- Data exfiltration dominated at 19.2%, primarily targeting system prompts and RAG context
- RAG poisoning surged to 10% of all threats, exploiting document retrieval systems
My take:
- The observed threats map cleanly to the Promptware Kill Chain I covered earlier.
- The inter-agent attacks are particularly concerning considering the growth of OpenClaw agents.
- RAG poisoning is trending upward. Alarming, considering a recent advancement in achieving a ~100% retrieval of a poisoned document.
RAXE Threat Intelligence Report
The Promptware Kill Chain
Overcoming the Retrieval Barrier
