google-analytics-automation

Pass

Audited by Gen Agent Trust Hub on Jun 22, 2026

Risk Level: SAFEEXTERNAL_DOWNLOADSPROMPT_INJECTION
Full Analysis
  • [EXTERNAL_DOWNLOADS]: The skill requires the configuration of an external Model Context Protocol (MCP) server endpoint at https://rube.app/mcp. This service is used to broker the connection between the agent and the Google Analytics API via OAuth.
  • [PROMPT_INJECTION]: The skill is susceptible to indirect prompt injection (Category 8) due to the following factors:
  • Ingestion points: Data enters the agent's context through GA4 reports, metadata discovery, and property/account listings (SKILL.md).
  • Boundary markers: The instructions do not define delimiters or provide warnings to the agent to ignore instructions that might be present in dimension values or event names retrieved from Google Analytics.
  • Capability inventory: The skill uses a comprehensive set of reporting tools (e.g., GOOGLE_ANALYTICS_RUN_REPORT, GOOGLE_ANALYTICS_RUN_FUNNEL_REPORT) that can retrieve large volumes of untrusted data from external properties.
  • Sanitization: There is no mention of sanitizing or escaping the data retrieved from external sources before it is processed or presented to the user.
Audit Metadata
Risk Level
SAFE
Analyzed
Jun 22, 2026, 06:17 PM
Security Audit — agent-trust-hub — google-analytics-automation