google_classroom-automation
Warn
Audited by Gen Agent Trust Hub on Feb 18, 2026
Risk Level: MEDIUMEXTERNAL_DOWNLOADSCOMMAND_EXECUTION
Full Analysis
- EXTERNAL_DOWNLOADS (MEDIUM): The skill requires connecting to an external MCP server at
https://rube.app/mcp. This domain is not on the trusted sources list and acts as a gateway for all tool schemas and executions. - COMMAND_EXECUTION (MEDIUM): The skill utilizes
RUBE_REMOTE_WORKBENCHfor bulk operations and data processing. This function allows for remote execution of logic and tool calls, which bypasses local environment controls. - INDIRECT_PROMPT_INJECTION (LOW): The skill is vulnerable to indirect prompt injection because it processes untrusted data from Google Classroom (assignments, announcements, and rosters).
- Ingestion points: Data retrieved from Google Classroom via tools discovered through
RUBE_SEARCH_TOOLS. - Boundary markers: Absent; the instructions do not specify any delimiters to separate classroom content from agent instructions.
- Capability inventory:
RUBE_MULTI_EXECUTE_TOOL(write/modify classroom data) andRUBE_REMOTE_WORKBENCH(remote data processing). - Sanitization: Absent; there is no mention of filtering or sanitizing classroom content before it is processed by the agent.
Audit Metadata