one-drive-automation

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

• Third-party content exposure detected (medium risk: 0.30). The workflow involves searching, reading, and downloading files from OneDrive, which can ingest outsider-authored document content and file text if shared files contain prompt injections.

MEDIUM W012: Unverifiable external dependency detected (runtime URL that controls agent).

• Potentially malicious external URL detected (high risk: 0.70). The skill references an external Model Context Protocol (MCP) server endpoint (https://rube.app/mcp) which is used as an operational dependency configuration for setup and runtime interaction with Rube MCP tools, but rube.app lacks strong/verifiable first-party provenance, placing it in the high-risk tier.