google-analytics

Pass

Audited by Gen Agent Trust Hub on Feb 19, 2026

Risk Level: SAFEPROMPT_INJECTION
Full Analysis
  • [Indirect Prompt Injection] (LOW): The skill ingests data from the Google Analytics API, which includes strings like page titles and campaign names that could be manipulated by external parties to influence agent behavior.
  • Ingestion points: Data retrieved from Google Analytics properties via ga_client.py and analyze.py.
  • Boundary markers: No explicit delimiters or instructions to ignore embedded commands are present in the documentation.
  • Capability inventory: Data fetching, metric analysis, and script execution.
  • Sanitization: No sanitization or validation of the retrieved metadata is mentioned.
  • [Data Exposure & Exfiltration] (SAFE): The skill correctly identifies the need for secure credential management, instructing users to use environment variables and avoid committing service account keys to version control.
  • [Unverifiable Dependencies & Remote Code Execution] (SAFE): All dependencies listed (google-analytics-data, python-dotenv, pandas) are well-known, standard libraries from the official Python Package Index (PyPI).
Audit Metadata
Risk Level
SAFE
Analyzed
Feb 19, 2026, 03:51 PM