Beyond Prompt Injection: The Tool Update Gap in LLM Agent Security
cs.CR, cs.AI
Submitted: 2026-11-01
Updated: 2026-11-01
Comments: 12 pages, 5 figures
Code: https://github.com/containers/bubblewrap
License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
Terminology
Sources
- ETDI: Mitigating Tool Squatting and Rug Pull Attacks in Model Context Protocol (MCP) by using OAuth-Enhanced Tool Definitions and Policy-Based Access Control
- Overcoming the Retrieval Barrier: Indirect Prompt Injection in the Wild for LLM Systems
- Defeating Prompt Injections by Design
- Not what you've signed up for: Compromising Real-World LLM-Integrated Applications with Indirect Prompt Injection
- MalTool: Malicious Tool Attacks on LLM Agents
- Model Context Protocol Threat Modeling and Analyzing Vulnerabilities to Prompt Injection with Tool Poisoning
- Cloak and Detonate: Scanner Evasion and Dynamic Detection of Agent Skill Malware
- Exploiting LLM Agent Supply Chains via Payload-less Skills
- Supply-Chain Poisoning Attacks Against LLM Coding Agent Skill Ecosystems
- Acoda: Adversarial Code Obfuscation for Defending against LLM-based Analysis
- How are AI agents used? Evidence from 177,000 MCP tools
- "Elementary, My Dear Watson." Detecting Malicious Skills via Neuro-Symbolic Reasoning across Heterogeneous Artifacts
- MCPTox: A Benchmark for Tool Poisoning Attack on Real-World MCP Servers
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