googledocs-automation

Pass

Audited by Gen Agent Trust Hub on Jun 15, 2026

Risk Level: SAFEPROMPT_INJECTIONEXTERNAL_DOWNLOADS
Full Analysis
  • [EXTERNAL_DOWNLOADS]: Connects to the vendor's official MCP server endpoint at https://rube.app/mcp and references documentation at composio.dev.
  • [PROMPT_INJECTION]: The skill is susceptible to indirect prompt injection due to its document reading and modification capabilities.
  • Ingestion points: Data enters the context from existing Google Docs via GOOGLEDOCS_GET_DOCUMENT_BY_ID and GOOGLEDOCS_SEARCH_DOCUMENTS (SKILL.md).
  • Boundary markers: No explicit boundary markers or instructions to ignore embedded commands are provided when processing document content.
  • Capability inventory: The skill has significant write capabilities, including GOOGLEDOCS_UPDATE_DOCUMENT_MARKDOWN, GOOGLEDOCS_REPLACE_ALL_TEXT, and GOOGLEDOCS_INSERT_TEXT_ACTION (SKILL.md).
  • Sanitization: No evidence of content sanitization or validation is present for data retrieved from external sources.
Audit Metadata
Risk Level
SAFE
Analyzed
Jun 15, 2026, 02:24 AM
Security Audit — agent-trust-hub — googledocs-automation