ClawGuard: A Runtime Security Framework for Tool-Augmented LLM Agents Against Indirect Prompt Injection

Abstract

Tool-augmented Large Language Model (LLM) agents have demonstrated impressive capabilities in automating complex, multi-step real-world tasks, yet remain vulnerable to indirect prompt injection. Adversaries exploit this weakness by embedding malicious instructions within tool-returned content, which agents directly incorporate into their conversation history as trusted observations. This vulnerability manifests across three primary attack channels: web and local content injection, MCP server inj

Categories

Framework mappings

Suggested from the entry's categories.

@misc{zhao2026clawguard,
  title = {{ClawGuard: A Runtime Security Framework for Tool-Augmented LLM Agents Against Indirect Prompt Injection}},
  author = {Wei Zhao and Zhe Li and Peixin Zhang and Jun Sun},
  year = {2026},
  month = apr,
  eprint = {2604.11790},
  archivePrefix = {arXiv},
  url = {https://arxiv.org/abs/2604.11790}
}