googlesheets-automation

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

• Third-party content exposure detected (high risk: 1.00). The skill's SKILL.md requires reading and interpreting arbitrary Google Sheets content (e.g., GOOGLESHEETS_BATCH_GET, GOOGLESHEETS_VALUES_GET, GOOGLESHEETS_LOOKUP_SPREADSHEET_ROW and related calls) which can be user-generated or publicly shared and that data is used to drive upserts, lookups, formatting and other agent actions—exposing the agent to untrusted third-party content that could inject instructions.

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

• Potentially malicious external URL detected (high risk: 1.00). This skill explicitly requires adding and using the MCP server at https://rube.app/mcp and instructs calling RUBE_SEARCH_TOOLS to fetch current tool schemas at runtime, meaning remote content from that URL directly controls agent tool prompts/behavior and is a required dependency.