ga4
Pass
Audited by Gen Agent Trust Hub on Sep 26, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [SAFE]: The skill uses environment variables (
GOOGLE_CLIENT_ID,GOOGLE_CLIENT_SECRET,GOOGLE_REFRESH_TOKEN) for authentication, which is a standard and secure practice to avoid hardcoding secrets. - [SAFE]: All network operations are directed to well-known Google service domains (
accounts.google.com,oauth2.googleapis.com,analyticsdata.googleapis.com) for OAuth and data retrieval. - [INDIRECT_PROMPT_INJECTION]: The skill processes external data from the Google Analytics API (such as page titles or dimensions).
- Ingestion points: The
scripts/ga4_query.pyscript retrieves metrics and dimensions from the GA4 property. - Boundary markers: None are present in the script's output, which generates plain text tables, CSV, or JSON.
- Capability inventory: The agent can execute these Python scripts to interact with the API and display results.
- Sanitization: Data retrieved from the API is displayed as-is without filtering, creating a minimal surface for indirect prompt injection if an attacker were to poison analytics data (e.g., via malicious page titles).
Audit Metadata