google-analytics

Pass

Audited by Gen Agent Trust Hub on Sep 17, 2026

Risk Level: SAFEINDIRECT_PROMPT_INJECTIONEXTERNAL_DOWNLOADS
Full Analysis
  • [INDIRECT_PROMPT_INJECTION]: The skill ingests data from the Google Analytics Data API, creating a surface for indirect prompt injection where malicious content in website metadata could influence the agent.
  • Ingestion points: Data is fetched from the external Google Analytics API via scripts/ga_client.py.
  • Boundary markers: The skill lacks explicit delimiters or instructions to the agent to ignore potentially malicious commands embedded within the retrieved analytics data.
  • Capability inventory: The scripts/analyze.py and scripts/ga_client.py scripts have the ability to write report files to the local filesystem.
  • Sanitization: While the skill includes path validation to prevent directory traversal, it does not sanitize the content of the analytics data for potential prompt injection markers.
  • [EXTERNAL_DOWNLOADS]: The skill instructions guide the user to download the skill and install necessary dependencies from well-known sources.
  • Fetches the skill repository from the author's GitHub repository (thatrebeccarae/claude-marketing).
  • Installs standard Python packages including google-analytics-data, python-dotenv, and pandas.
Audit Metadata
Risk Level
SAFE
Analyzed
Sep 17, 2026, 08:54 PM
Security Audit — agent-trust-hub — google-analytics