llm-analytics-setup
Pass
Audited by Gen Agent Trust Hub on Sep 19, 2026
Risk Level: SAFE
Full Analysis
- [SAFE]: The skill consists entirely of documentation and code examples for setting up PostHog LLM analytics across a wide range of providers (OpenAI, Anthropic, Google, etc.).
- [SAFE]: All mentioned dependencies (e.g., posthog, openai, anthropic) are official SDKs from established organizations, and the instructions follow standard installation patterns via package managers.
- [SAFE]: The code snippets use placeholders for sensitive credentials (e.g., "<ph_project_token>", "your_openai_api_key") and explicitly instruct the user to use environment variables instead of hardcoding secrets.
- [SAFE]: The documentation includes security-conscious guidelines, such as warning the user to never send PII in event properties and providing instructions on how to handle identifying data correctly.
Audit Metadata