one-drive-automation
Pass
Audited by Gen Agent Trust Hub on Oct 26, 2026
Risk Level: SAFEEXTERNAL_DOWNLOADSINDIRECT_PROMPT_INJECTION
Full Analysis
- [EXTERNAL_DOWNLOADS]: The skill instructs the user to add an external MCP server endpoint at
https://rube.app/mcpto enable its functionality. - [INDIRECT_PROMPT_INJECTION]: The skill processes untrusted content from OneDrive, creating a surface for indirect prompt injection attacks.
- Ingestion points: Untrusted data enters the agent context through tools such as
ONE_DRIVE_SEARCH_ITEMS,ONE_DRIVE_GET_ITEM, andONE_DRIVE_ONEDRIVE_LIST_ITEMSas described inSKILL.md. - Boundary markers: No specific boundary markers or instructions to ignore embedded commands are present in the documentation to protect against malicious data content.
- Capability inventory: The skill includes high-impact tools for file deletion (
ONE_DRIVE_DELETE_ITEM), permission modification (ONE_DRIVE_INVITE_USER_TO_DRIVE_ITEM), and file uploads (ONE_DRIVE_ONEDRIVE_UPLOAD_FILE), which could be abused if an injection occurs. - Sanitization: There is no evidence of sanitization or filtering applied to the metadata or file content retrieved from OneDrive before it is processed by the agent.
Audit Metadata