Work

Beyond Max Tokens: Stealthy Resource Amplification via Tool Calling Chains in LLM Agents

Year: 2026
Type: conference-paper
Abstract: The agent-tool interaction loop is a critical attack surface for modern Large Language Model (LLM) agents.Existing denial-ofservice (DoS) attacks typically function at the user-prompt or retrieval-augmented generation (RAG) context layer and are inherently single-turn in nature.This limitation restricts cost amplification and diminishes stealth in goal-oriented workflows.To address these issues, we propose a stealthy, multi-turn economic DoS attack at the tool layer under the Model Context Protocol (MCP).By editing only text-visible fields and implementing a stateful, completeness-gated return policy, our malicious server preserves tool identity and the terminal benign payload while steering agents into prolonged, verbose tool-calling chains.We optimize these text-only edits with Monte Carlo Tree Search (MCTS) to maximize cost under a task-success constraint.Across six LLMs on ToolBench and BFCL benchmarks, our attack yields trajectories over 60K tokens, increases per-query cost by up to 658×, raises energy by 100-560×, and pushes GPU key-value (KV) cache occupancy to 35-74%.Representative prompt filters and output or trajectory monitors seldom detect these attacks, highlighting the need for defenses that safeguard agentic processes rather than focusing solely on final outcomes.
Language: English
Open Access status: bronze
OpenAlex ID: W7124732130
FWCI: 12.17
Cites: 48
Cited by: 20
Related to: 10