MCP-SandboxScan: WASM-based Secure Execution and Runtime Analysis for MCP Tools

• URL: http://arxiv.org/abs/2601.01241v1
• Date: Sat, 03 Jan 2026 17:25:38 GMT
• Title: MCP-SandboxScan: WASM-based Secure Execution and Runtime Analysis for MCP Tools
• Authors: Zhuoran Tan, Run Hao, Jeremy Singer, Yutian Tang, Christos Anagnostopoulos,
• Abstract summary: Tool executions can introduce runtime-only behaviors, including prompt injection and unintended exposure of external inputs.<n>We present MCP-SandboxScan, a framework that safely executes untrusted tools inside a WebAssembly/WASI sandbox.
• Score: 3.1835741342145063
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: Tool-augmented LLM agents raise new security risks: tool executions can introduce runtime-only behaviors, including prompt injection and unintended exposure of external inputs (e.g., environment secrets or local files). While existing scanners often focus on static artifacts, analyzing runtime behavior is challenging because directly executing untrusted tools can itself be dangerous. We present MCP-SandboxScan, a lightweight framework motivated by the Model Context Protocol (MCP) that safely executes untrusted tools inside a WebAssembly/WASI sandbox and produces auditable reports of external-to-sink exposures. Our prototype (i) extracts LLM-relevant sinks from runtime outputs (prompt/messages and structured tool-return fields), (ii) instantiates external-input candidates from environment values, mounted file contents, and output-surfaced HTTP fetch intents, and (iii) links sources to sinks via snippet-based substring matching. Case studies on three representative tools show that MCP-SandboxScan can surface provenance evidence when external inputs appear in prompt/messages or tool-return payloads, and can expose filesystem capability violations as runtime evidence. We further compare against a lightweight static string-signature baseline and use a micro-benchmark to characterize false negatives under transformations and false positives from short-token collisions.

Related papers

• Multi-Agent Taint Specification Extraction for Vulnerability Detection [49.27772068704498]
  Static Application Security Testing (SAST) tools using taint analysis are widely viewed as providing higher-quality vulnerability detection results.<n>We present SemTaint, a multi-agent system that strategically combines the semantic understanding of Large Language Models (LLMs) with traditional static program analysis.<n>We integrate SemTaint with CodeQL, a state-of-the-art SAST tool, and demonstrate its effectiveness by detecting 106 of 162 vulnerabilities previously undetectable by CodeQL.
  arXiv  Detail & Related papers  (2026-01-15T21:31:51Z)
• Securing the Model Context Protocol: Defending LLMs Against Tool Poisoning and Adversarial Attacks [8.419049623790618]
  This work analyzes three classes of semantic attacks on MCP-integrated systems.<n>We introduce a layered security framework with three components: RSA-based manifest signing to enforce descriptor integrity, LLM-on-LLM semantic vetting to detect suspicious tool definitions, and lightweight guardrails that block anomalous tool behavior at runtime.<n>Our results show that the proposed framework reduces unsafe tool invocation rates without model fine-tuning or internal modification.
  arXiv  Detail & Related papers  (2025-12-06T20:07:58Z)
• InspectCoder: Dynamic Analysis-Enabled Self Repair through interactive LLM-Debugger Collaboration [71.18377595277018]
  Large Language Models (LLMs) frequently generate buggy code with complex logic errors that are challenging to diagnose.<n>We present InspectCoder, the first agentic program repair system that empowers LLMs to actively conduct dynamic analysis via interactive debugger control.
  arXiv  Detail & Related papers  (2025-10-21T06:26:29Z)
• Mind Your Server: A Systematic Study of Parasitic Toolchain Attacks on the MCP Ecosystem [13.95558554298296]
  Large language models (LLMs) are increasingly integrated with external systems through the Model Context Protocol (MCP)<n>In this paper, we reveal a new class of attacks, Parasitic Toolchain Attacks, instantiated as MCP Unintended Privacy Disclosure (MCP-UPD)<n>The malicious logic infiltrates the toolchain and unfolds in three phases: Parasitic Ingestion, Privacy Collection, and Privacy Disclosure, culminating in stealthy exfiltration of private data.
  arXiv  Detail & Related papers  (2025-09-08T11:35:32Z)
• EchoLeak: The First Real-World Zero-Click Prompt Injection Exploit in a Production LLM System [0.0]
  Large language model (LLM) assistants are increasingly integrated into enterprise, raising new security concerns.<n>This paper presents an in-depth case study of EchoLeak-2025-32711, a zero-click prompt injection vulnerability in Microsoft 365 Copilot.
  arXiv  Detail & Related papers  (2025-09-06T04:06:01Z)
• DRIFT: Dynamic Rule-Based Defense with Injection Isolation for Securing LLM Agents [52.92354372596197]
  Large Language Models (LLMs) are increasingly central to agentic systems due to their strong reasoning and planning capabilities.<n>This interaction also introduces the risk of prompt injection attacks, where malicious inputs from external sources can mislead the agent's behavior.<n>We propose a Dynamic Rule-based Isolation Framework for Trustworthy agentic systems, which enforces both control and data-level constraints.
  arXiv  Detail & Related papers  (2025-06-13T05:01:09Z)
• Invisible Prompts, Visible Threats: Malicious Font Injection in External Resources for Large Language Models [29.879456712405204]
  Large Language Models (LLMs) are increasingly equipped with capabilities of real-time web search and integrated with protocols like Model Context Protocol (MCP)<n>This extension could introduce new security vulnerabilities.<n>We present a systematic investigation of LLM vulnerabilities to hidden adversarial prompts through malicious font injection in external resources like webpages.
  arXiv  Detail & Related papers  (2025-05-22T17:36:33Z)
• MCP Safety Audit: LLMs with the Model Context Protocol Allow Major Security Exploits [0.0]
  The Model Context Protocol (MCP) is an open protocol that standardizes API calls to large language models (LLMs), data sources, and agentic tools.<n>We show that the current MCP design carries a wide range of security risks for end users.<n>We introduce a safety auditing tool, MCPSafetyScanner, to assess the security of an arbitrary MCP server.
  arXiv  Detail & Related papers  (2025-04-02T21:46:02Z)
• The Impact of SBOM Generators on Vulnerability Assessment in Python: A Comparison and a Novel Approach [56.4040698609393]
  Software Bill of Materials (SBOM) has been promoted as a tool to increase transparency and verifiability in software composition. Current SBOM generation tools often suffer from inaccuracies in identifying components and dependencies. We propose PIP-sbom, a novel pip-inspired solution that addresses their shortcomings.
  arXiv  Detail & Related papers  (2024-09-10T10:12:37Z)
• Get my drift? Catching LLM Task Drift with Activation Deltas [55.75645403965326]
  Task drift allows attackers to exfiltrate data or influence the LLM's output for other users.<n>We show that a simple linear classifier can detect drift with near-perfect ROC AUC on an out-of-distribution test set.<n>We observe that this approach generalizes surprisingly well to unseen task domains, such as prompt injections, jailbreaks, and malicious instructions.
  arXiv  Detail & Related papers  (2024-06-02T16:53:21Z)
• JITScanner: Just-in-Time Executable Page Check in the Linux Operating System [6.725792100548271]
  JITScanner is developed as a Linux-oriented package built upon a Loadable Kernel Module (LKM) It integrates a user-level component that communicates efficiently with the LKM using scalable multi-processor/core technology. JITScanner's effectiveness in detecting malware programs and its minimal intrusion in normal runtime scenarios have been extensively tested.
  arXiv  Detail & Related papers  (2024-04-25T17:00:08Z)
• Adversarial EXEmples: A Survey and Experimental Evaluation of Practical Attacks on Machine Learning for Windows Malware Detection [67.53296659361598]
  adversarial EXEmples can bypass machine learning-based detection by perturbing relatively few input bytes. We develop a unifying framework that does not only encompass and generalize previous attacks against machine-learning models, but also includes three novel attacks. These attacks, named Full DOS, Extend and Shift, inject the adversarial payload by respectively manipulating the DOS header, extending it, and shifting the content of the first section.
  arXiv  Detail & Related papers  (2020-08-17T07:16:57Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.