excel-mcp

Warn

Audited by Snyk on Mar 11, 2026

Risk Level: MEDIUM
Full Analysis

MEDIUM W011: Third-party content exposure detected (indirect prompt injection risk).

  • Third-party content exposure detected (high risk: 0.70). The skill's required Power Query workflow explicitly uses powerquery(action: "evaluate"/"create"/"refresh") and documents loading from "database/web source" (see references/powerquery.md and SKILL.md), so the agent will fetch and read arbitrary third‑party web/database sources' data as part of its normal execution, allowing that untrusted content to influence subsequent tool actions.
Audit Metadata
Risk Level
MEDIUM
Analyzed
Mar 11, 2026, 04:36 AM