ShadowBench-MCP: Measuring Shadow Invocations in MCP-Style Tool Routing

Summary

ShadowBench-MCP is a benchmark that measures shadow invocation, where an LLM router selects a riskier execution path for a task-preserving request, possibly skipping validation, provenance, staging, redaction or audit controls. In a single-router study using a Groq-hosted qwen/qwen3-32b router across 96 comparisons in six workflows, efficiency-first routing produced a 29.2% shadow-invocation rate and a 26.7% safety-tool skip rate. Policy-aware routing reduced these to 4.2% and 1.7%, an 85.7% relative reduction, and pre-execution signals separated shadow routes with ROC AUC up to 0.94.

Mitigation

Policy-aware routing reduced shadow invocations and safety-tool skips in the study. The source does not present this as a general fix and makes no claim of universal vulnerability.

Topics

• Model Context Protocol

Related items

• HighCVE-2026-123818: LMDeploy is a toolkit for compressing, deploying, and serving large language models. From 0.12.3 until 0.15.0…Similar attack · NVD/CVE Database
• HighGHSA-vvr2-h2jp-838m: Code Graph RAG: MCP paginated read_file path traversal / arbitrary file readSimilar attack · GitHub Advisory Database
• InfoSuppression Is Not Erasure: Mechanistic Analysis and Reactivation Boundaries of Subspace Projection for LoRA Backdoor DefenseSimilar attack · Arxiv (cs.CR + cs.CL + cs.LG)
• MediumAttackers Crash Claude's 'Office Party' Flaw to Run Malicious Code on LinuxSimilar attack · Dark Reading
• InfoSay Shibboleth: Fingerprinting the LLMs and Harnesses Behind Agentic AttacksSimilar attack · Arxiv (cs.CR + cs.CL + cs.LG)