googlesheets-automation

MEDIUM W011: Third-party content exposure detected (indirect prompt injection risk).

• Third-party content exposure detected (low risk: 0.10). The workflow only uses Google Sheets toolkit tools to read/write specific spreadsheet ranges selected via user-supplied spreadsheet/tab identifiers, and the runtime reads free text from the target spreadsheet cells rather than from any outsider-authored queue/feed the workflow automatically monitors; thus outsider-controlled cell content is not clearly an “indirect prompt injection” vector beyond the user’s explicitly targeted spreadsheet data.

MEDIUM W012: Unverifiable external dependency detected (runtime URL that controls agent).

• Potentially malicious external URL detected (high risk: 0.90). The skill explicitly requires contacting the external MCP server https://rube.app/mcp at runtime (via RUBE_SEARCH_TOOLS) to fetch tool schemas that directly determine the agent's available tools/instructions, making it a required remote runtime dependency.