google-office
Pass
Audited by Gen Agent Trust Hub on Jul 30, 2026
Risk Level: SAFECOMMAND_EXECUTIONEXTERNAL_DOWNLOADSPROMPT_INJECTION
Full Analysis
- [COMMAND_EXECUTION]: The skill uses the 'goog' CLI tool to execute shell commands for interacting with Google services.
- [EXTERNAL_DOWNLOADS]: The skill references the author's GitHub repository for installation and configuration of the required CLI tool.
- [PROMPT_INJECTION]: The skill processes data from external sources like Gmail and Google Drive, which is a potential surface for indirect prompt injection.
- Ingestion points: Gmail search, message reading, and file downloads via 'goog' commands.
- Boundary markers: No explicit delimiters are used to separate ingested content from system instructions.
- Capability inventory: The agent can execute CLI commands and perform file uploads and downloads.
- Sanitization: No specific filtering or sanitization of content retrieved from Google Workspace is described.
Audit Metadata