analytics-tracking-automation

Warn

Audited by Gen Agent Trust Hub on May 24, 2026

Risk Level: MEDIUMEXTERNAL_DOWNLOADSCOMMAND_EXECUTIONCREDENTIALS_UNSAFEPROMPT_INJECTION
Full Analysis
  • [EXTERNAL_DOWNLOADS]: The skill instructions direct users to clone and install code from a remote GitHub repository (github.com/jtrackingai/analytics-tracking-automation.git) using git clone and npm install.
  • [COMMAND_EXECUTION]: The workflow relies on executing shell commands, including environment setup (npm run install:skills) and a specialized CLI tool (npx event-tracking) used for site analysis and GTM synchronization.
  • [CREDENTIALS_UNSAFE]: The skill handles sensitive Google OAuth 2.0 credentials (GOOGLE_CLIENT_ID, GOOGLE_CLIENT_SECRET) and caches authorization tokens in a local file (oauth-tokens.json) for persistence.
  • [PROMPT_INJECTION]: The skill is susceptible to indirect prompt injection because it crawls and processes content from external websites.
  • Ingestion points: Website content is ingested during npx event-tracking init and audit commands.
  • Boundary markers: No specific boundary markers or safety instructions are mentioned to prevent the agent from following directions embedded in crawled sites.
  • Capability inventory: The skill possesses the ability to modify and publish Google Tag Manager containers via API, execute browser automation with Playwright, and write to the local file system.
  • Sanitization: No evidence of sanitization or filtering for crawled content is provided in the documentation.
Audit Metadata
Risk Level
MEDIUM
Analyzed
May 24, 2026, 08:56 PM
Security Audit — agent-trust-hub — analytics-tracking-automation