google-analytics-automation
Pass
Audited by Gen Agent Trust Hub on Feb 20, 2026
Risk Level: SAFEPROMPT_INJECTION
Full Analysis
- [Indirect Prompt Injection] (LOW): The skill processes untrusted data from the Google Analytics API. (1) Ingestion points: Data entering via GOOGLE_ANALYTICS_RUN_REPORT and GOOGLE_ANALYTICS_LIST_ACCOUNTS. (2) Boundary markers: No explicit delimiters are used to separate GA4 data from agent instructions. (3) Capability inventory: The skill utilizes GA4 reporting and management tools; it does not request shell or file-write access. (4) Sanitization: No sanitization of API responses is defined.
- [Data Exposure & Exfiltration] (SAFE): Sensitive data access is handled through authenticated OAuth connections managed via RUBE_MANAGE_CONNECTIONS. No unauthorized exfiltration or hardcoded credentials were found.
- [Remote Code Execution] (SAFE): The skill consists of instructional content for existing tools and does not perform script execution or package installation.
Audit Metadata