google-drive-automation
Pass
Audited by Gen Agent Trust Hub on Oct 8, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTIONEXTERNAL_DOWNLOADS
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill facilitates the ingestion of untrusted data from external Google Drive files, which could contain instructions aimed at manipulating the agent's logic.
- Ingestion points: Data is retrieved via
GOOGLEDRIVE_FIND_FILE,GOOGLEDRIVE_DOWNLOAD_FILE, andGOOGLEDRIVE_GET_FILE_METADATA(SKILL.md). - Boundary markers: The skill lacks explicit instructions or markers to distinguish between data and instructions when processing file content.
- Capability inventory: The agent is granted capabilities to upload files, modify sharing permissions (
GOOGLEDRIVE_ADD_FILE_SHARING_PREFERENCE), and delete permissions, providing a functional path for potential injection impact. - Sanitization: There is no evidence of content sanitization or validation for the retrieved file data.
- [EXTERNAL_DOWNLOADS]: The skill directs the user to connect to an external MCP server at
https://rube.app/mcpand references toolkit documentation atcomposio.dev. These are standard functional requirements for the Composio integration used by the skill.
Audit Metadata