google-analytics-automation
Pass
Audited by Gen Agent Trust Hub on Oct 31, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTIONEXTERNAL_DOWNLOADS
Full Analysis
- [EXTERNAL_DOWNLOADS]: The skill utilizes the Rube MCP server endpoint at https://rube.app/mcp for its core functionality.
- [INDIRECT_PROMPT_INJECTION]: The skill processes data from external Google Analytics accounts, creating a potential surface for indirect prompt injection.
- Ingestion points: Data enters the agent's context through tools like GOOGLE_ANALYTICS_LIST_ACCOUNTS, GOOGLE_ANALYTICS_LIST_PROPERTIES, and GOOGLE_ANALYTICS_RUN_REPORT as described in SKILL.md.
- Boundary markers: The instructions do not specify any delimiters or warnings to ignore instructions embedded within the retrieved data.
- Capability inventory: The skill provides capabilities to list accounts, list properties, and execute various reporting queries (standard, batch, pivot, and funnel).
- Sanitization: No explicit sanitization or validation of the data returned by the Google Analytics API is mentioned in the skill instructions.
Audit Metadata