Persistent Billable State: Denial-of-Wallet Attacks and Defenses in Tool-Calling LLM Agents

arXiv:2609.28585 · cs.CR, cs.AI · Submitted 2026-09-23 · Read on arXiv

cs.CR, cs.AI

Submitted: 2026-09-23

Updated: 2026-09-23

Comments: 22 pages, 14 figures, 13 tables

License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/

Terminology

• Trace — 23× in this paper · explained in 2 episodes
• Calibration — 9× in this paper · explained in 7 episodes
• Core — 9× in this paper · explained in 2 episodes
• Model Context Protocol — 6× in this paper
• Provenance — 5× in this paper · explained in 3 episodes
• Benchmark — 4× in this paper · explained in 2 episodes
• Cost Amplification Factor — 4× in this paper
• Ablation — 3× in this paper · explained in 1 episode
• Benchmarking — 3× in this paper · explained in 3 episodes
• Accuracy — 1× in this paper · explained in 1 episode
• Adaptive Strategy — 1× in this paper · explained in 1 episode
• Aggregation — 1× in this paper · explained in 1 episode
• Consistency — 1× in this paper · explained in 3 episodes
• Model Context Protocol (MCP) — 1× in this paper · explained in 8 episodes
• Multi-Agent System — 1× in this paper · explained in 6 episodes
• Objective Mismatch — 1× in this paper · explained in 2 episodes
• Robustness — 1× in this paper · explained in 5 episodes
• Tokenization — 1× in this paper · explained in 2 episodes
• Verification — 1× in this paper · explained in 2 episodes

Sources

• State of AI: An Empirical 100 Trillion Token Study with OpenRouter
• Design Patterns for Securing LLM Agents against Prompt Injections
• Talk is (Not) Cheap: A Taxonomy and Benchmark Coverage Audit for LLM Attacks
• Clawdrain: Exploiting Tool-Calling Chains for Stealthy Token Exhaustion in OpenClaw Agents
• Token Budgets: An Empirical Catalog of 63 LLM-Agent Budget-Overrun Incidents, with an Affine-Typed Rust Mitigation as a Case Study
• Overthinking Loops in Agents: A Structural Risk via MCP Tools
• Prompt Injection attack against LLM-integrated Applications
• Agent Contracts: A Formal Framework for Resource-Bounded Autonomous AI Systems
• Skill-Inject: Measuring Agent Vulnerability to Skill File Attacks
• LeechHijack: Covert Computational Resource Exploitation in Intelligent Agent Systems
• The Landscape of Prompt Injection Threats in LLM Agents: From Taxonomy to Analysis
• Beyond Max Tokens: Stealthy Resource Amplification via Tool Calling Chains in LLM Agents
• A New Era in LLM Security: Exploring Security Concerns in Real-World LLM-based Systems
• From Shield to Target: Denial-of-Service Attacks on LLM-Based Agent Guardrails

Related papers

• SoK: AI-Augmented Binary Reversing
• Relaxed Sender Anonymity for CBDC Interbank Settlement: A Zero-Knowledge Approach on Permissioned EVM
• Calibration-Family Overfit: Why Trusted Sabotage Monitors Don't Transfer Across Lineages
• Efficient Fuzzy PSI under One-Sided Assumptions
• Sealing the Audit-Runtime Gap for LLM Skills
• Token Composition: A Graph Based on EVM Logs