OverServe: Resource Amplification Attacks on SaaS Agents via Tool--Prompt Co-Design
cs.CR, cs.AI, cs.SE
Submitted: 2026-11-10
Updated: 2026-11-17
Code: https://github.com/cisco-ai-defense/mcp-scanner
Terminology
Sources
- Nemotron 3 Super: Open, Efficient Mixture-of-Experts Hybrid Mamba-Transformer Model for Agentic Reasoning
- BrowseComp-Plus: A More Fair and Transparent Evaluation Benchmark of Deep-Research Agent
- Clawdrain: Exploiting Tool-Calling Chains for Stealthy Token Exhaustion in OpenClaw Agents
- GLM-5: from Vibe Coding to Agentic Engineering
- When Agents Do Not Stop: Uncovering Infinite Agentic Loops in LLM Agents
- From Component Manipulation to System Compromise: Understanding and Detecting Malicious MCP Servers
- OverThink: Slowdown Attacks on Reasoning LLMs
- Overthinking Loops in Agents: A Structural Risk via MCP Tools
- A2M: Trace-Optimized Agent Hijacking in the MCP Ecosystem
- Sponge Tool Attack: Stealthy Denial-of-Efficiency against Tool-Augmented Agentic Reasoning
- MCP-ITP: An Automated Framework for Implicit Tool Poisoning in MCP
- OTora: A Unified Red Teaming Framework for Reasoning-Level Denial-of-Service in LLM Agents
- ReasoningBomb: A Stealthy Denial-of-Service Attack by Inducing Pathologically Long Reasoning in Large Reasoning Models
- EnterpriseOps-Gym: Environments and Evaluations for Stateful Agentic Planning and Tool Use in Enterprise Settings
- When Do Agent Loops Mistake Stagnation for Progress? Self-Evaluation Bias and Externally Grounded Verification in Long-Running Autonomous LLM Agent Loops
- Description-Code Inconsistency in Real-world MCP Servers: Measurement, Detection, and Security Implications
- WorkBench: a Benchmark Dataset for Agents in a Realistic Workplace Setting
- Qwen3 Technical Report
- Executable Code Actions Elicit Better LLM Agents
- DeepSeek-V4: Towards Highly Efficient Million-Token Context Intelligence
Related papers
- From Strategy Search to Policy Learning: MCTS-Guided Adversarial Co-Evolution for LLM Safety Alignment
- Privacy Leakage from Recurrent State in LLM Inference
- Incrementally Verifiable Oracle Aided Computation
- Privilege and confidentiality in generative AI workflows
- BadMoE: Backdooring Mixture-of-Experts LLMs via Routing-Aware Triggers and Task-Underutilized Experts
- CoVault: Secure, Scalable Analytics of Personal Data