one-drive-automation
Pass
Audited by Gen Agent Trust Hub on Jul 18, 2026
Risk Level: SAFE
Full Analysis
- [PROMPT_INJECTION]: The skill creates a surface for indirect prompt injection by ingesting untrusted data from OneDrive files and metadata. If a processed file contains malicious prompts, the agent may attempt to follow them using its available file operations. Ingestion points: File content and metadata retrieved via ONE_DRIVE_DOWNLOAD_FILE and ONE_DRIVE_SEARCH_ITEMS. Boundary markers: No delimiters or isolation instructions are present to protect the agent from embedded commands. Capability inventory: The skill provides extensive write and delete access, as well as permission management via ONE_DRIVE_DELETE_ITEM and ONE_DRIVE_INVITE_USER_TO_DRIVE_ITEM. Sanitization: The instructions do not specify any validation or filtering of content before processing.
- [EXTERNAL_DOWNLOADS]: The skill facilitates connection to an external MCP server at https://rube.app/mcp, which serves as the necessary gateway for OneDrive integration.
Audit Metadata