{"data":{"id":"cb41f35d-99fb-47c4-8b11-84ba4c4df643","title":"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.","solution":"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.","labels":["security","research"],"sourceUrl":"https://arxiv.org/abs/2611.11720v1","publishedAt":"2026-11-09T00:29:34.000Z","cveId":null,"cweIds":null,"cvssScore":null,"cvssSeverity":null,"severity":"info","attackType":["other"],"issueType":"research","affectedPackages":null,"affectedPackageNames":null,"affectedPackageRefs":null,"affectedVendors":[],"affectedVendorsRaw":["Groq","qwen/qwen3-32b"],"classifierModel":"claude-haiku-5-5","classifierPromptVersion":"v4","summaryPromptVersion":"v2","headline":null,"headlinePromptVersion":null,"cvssVector":null,"attackVector":null,"attackComplexity":null,"privilegesRequired":null,"userInteraction":null,"exploitMaturity":null,"epssScore":null,"epssCheckedAt":null,"kevDateAdded":null,"advisoryAliases":null,"affectedPackagesSource":null,"affectedPackagesCheckedAt":null,"patchAvailable":null,"disclosureDate":"2026-11-09T00:29:34.000Z","fixReleasedAt":null,"daysToFix":null,"fixCheckedAt":null,"capecIds":null,"crossRefCount":0,"attackSophistication":"moderate","impactType":["integrity","safety"],"aiComponentTargeted":"agent","llmSpecific":true,"classifierConfidence":0.9,"researchCategory":"preprint","atlasIds":null}}