Sponge Tool Attack: Stealthy Denial-of-Efficiency against Tool-Augmented Agentic Reasoning

Understand

Enabling large language models (LLMs) to solve complex reasoning tasks is a key step toward artificial general intelligence.

• Recent work augments LLMs with external tools to enable agentic reasoning, achieving high utility and efficiency in a plug-and-play manner.
• However, the inherent vulnerabilities of such methods to malicious manipulation of the tool-calling process remain largely unexplored.
• In this work, we identify a tool-specific attack surface and propose Sponge Tool Attack (STA), which disrupts agentic reasoning solely by rewriting the input prompt under a strict query-only access assumption.