The Agent Skills Directory

[SAFE]: The skill instructions and code snippets in the reference files follow standard and safe practices for web analytics implementation. No malicious command execution or persistence mechanisms are present.
[SAFE]: The skill references well-known technology services such as Google Analytics 4, Mixpanel, and Segment for its core functionality, which are recognized as safe external sources.
[INDIRECT_PROMPT_INJECTION]: The skill is designed to ingest and process project-specific context and user-provided tracking requirements, creating an attack surface common to developer-facing AI agents.
Ingestion points: Reads project-level context files such as .agents/product-marketing.md and parses user-supplied data layer or event tracking descriptions.
Boundary markers: Explicit boundary markers for external data ingestion are absent in the prompt instructions.
Capability inventory: Generates JavaScript configuration code and provides troubleshooting responses based on ingested data across all reference implementation files.
Sanitization: Includes instructions to validate data quality and proactively warns against the collection of Personally Identifiable Information (PII) in tracking properties.

analytics