one-drive-automation

Pass

Audited by Gen Agent Trust Hub on Apr 14, 2026

Risk Level: SAFEPROMPT_INJECTION
Full Analysis
  • [PROMPT_INJECTION]: Potential for Indirect Prompt Injection. * Ingestion points: Tools such as ONE_DRIVE_SEARCH_ITEMS and ONE_DRIVE_GET_ITEM are used to ingest file metadata and content from OneDrive into the agent's context. * Boundary markers: The skill does not define any delimiters or instructions to treat data retrieved from OneDrive as untrusted or isolated from primary instructions. * Capability inventory: The toolkit includes high-impact capabilities such as ONE_DRIVE_DELETE_ITEM (deletion), ONE_DRIVE_INVITE_USER_TO_DRIVE_ITEM (permission and sharing management), and ONE_DRIVE_MOVE_ITEM. * Sanitization: No logic is provided to sanitize, escape, or validate the content retrieved from the external drive before processing.
  • [EXTERNAL_DOWNLOADS]: The skill connects to an external MCP server at https://rube.app/mcp to provide the required OneDrive automation toolkit.
Audit Metadata
Risk Level
SAFE
Analyzed
Apr 14, 2026, 06:00 PM