google-analytics-automation
Pass
Audited by Gen Agent Trust Hub on Oct 27, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [SAFE]: The skill documents standard interactions with the Google Analytics API using predefined tool schemas. All external references are directed toward the official service endpoint (
rube.app) for the MCP integration. - [INDIRECT_PROMPT_INJECTION]: The skill facilitates the ingestion of data from external Google Analytics properties, which represents a potential attack surface for indirect prompt injection if property names or event metadata were to contain malicious instructions.
- Ingestion points: Tools such as
GOOGLE_ANALYTICS_RUN_REPORT,GOOGLE_ANALYTICS_LIST_ACCOUNTS, andGOOGLE_ANALYTICS_LIST_PROPERTIESfetch data from third-party GA4 accounts. - Boundary markers: The instructions do not specify the use of delimiters or warnings to isolate external data from the agent's core instructions.
- Capability inventory: The skill is scoped to reporting and property management; it does not contain high-privilege capabilities such as arbitrary command execution or local file system persistence.
- Sanitization: There are no explicit instructions for the agent to sanitize or validate the content returned by the Google Analytics API.
Audit Metadata