arXiv Machine Learning
MCPTox: A Benchmark for Tool Poisoning Attack on Real-World MCP Servers
Read the original on arXiv Machine Learning →The Flow has not summarised this story yet — read it at arXiv Machine Learning.
Related stories
arXiv AI
Jun 26
ShareLock: A Stealthy Multi-Tool Threshold Poisoning Attack Against MCP
arXiv:2606. 27027v1 Announce Type: cross Abstract: With the rapid evolution of LLM-driven agents, Model Context Protocol (MCP), an open protocol bridging LLMs with external tools, has quickly become foundational to modern agent ecosystems.
arXiv AI
Jul 24
IssueTrojanBench: Benchmarking AI Coding Agents Against Malicious Issue Requests
arXiv:2607. 20759v1 Announce Type: cross Abstract: AI coding agents powered by LLMs are increasingly integrated into real-world software development, where they generate, edit, and execute code with autonomous access to local files and tools.
arXiv AI
Sep 12
No-Box Vulnerability Analysis: Description-only Detection of Indirect Prompt Injection Vulnerabilities in MCP Servers
The paper introduces no‑box vulnerability analysis, a method that detects security flaws without system access or runtime interaction by examining only the functionality metadata of a target. Using this approach, the authors built MCPSEC to audit Model Context Protocol servers for indirect prompt injection vulnerabilities, evaluating it on 20 servers with 177 tools. MCPSEC identified 143 vulnerable tools, achieving 98.9% recall of verified vulnerabilities, outperforming an LLM baseline.
arXiv AI
Jul 21
STAC: When Innocent Tools Form Dangerous Chains for LLM Agents
arXiv:2509. 25624v3 Announce Type: replace-cross Abstract: As LLMs advance into autonomous agents with tool-use capabilities, they introduce security challenges that extend beyond traditional content-based LLM safety concerns.
arXiv AI
Jul 29
Hybrid Analysis for Secure MCP Tool Use in LLM Agents
arXiv:2607. 25297v1 Announce Type: cross Abstract: The rapid development of large language model (LLM) agents has enabled their broad adoption across diverse real-world tasks.
arXiv AI
Jul 7
Agent Data Injection Attacks are Realistic Threats to AI Agents
arXiv:2607. 05120v1 Announce Type: cross Abstract: AI agents act on behalf of user prompts, consuming external data and taking actions based on the agent context.