hydrogen-analytics-tracking
Pass
Audited by Gen Agent Trust Hub on May 28, 2026
Risk Level: SAFE
Full Analysis
- [EXTERNAL_DOWNLOADS]: The skill instructs users to load tracking scripts from well-known and trusted services, specifically Google Tag Manager (
googletagmanager.com) and Google Analytics (google-analytics.com). These are standard practices for analytics implementation and are considered safe. - [DATA_EXFILTRATION]: The core functionality involves sending tracking data (events, product views, purchases) to third-party vendors such as Google, Meta, and TikTok. The skill explicitly mandates server-side hashing for sensitive user data like email and phone numbers before transmission, which is a security best practice for data privacy.
- [COMMAND_EXECUTION]: The skill mentions local maintenance scripts (
scripts/search_shopify_docs.mjs) for searching documentation. While the code for these scripts is not provided, their described use case is benign. - [PROMPT_INJECTION]: No patterns of prompt injection, role-play overrides, or system prompt extraction instructions were detected in the skill instructions or reference files.
- [CREDENTIALS_UNSAFE]: The skill uses appropriate placeholders for secrets (e.g.,
GA4_API_SECRET,META_CAPI_ACCESS_TOKEN,SHOPIFY_WEBHOOK_SECRET) and provides clear instructions ingotchas.mdfor secret rotation and management, discouraging the storage of clear-text credentials. - [INDIRECT_PROMPT_INJECTION]: The skill creates an attack surface by ingesting data from external sources (Shopify webhooks and browser-side
sendBeaconrequests). However, it mitigates this risk by recommending strict schema validation and server-side processing, and it lacks dangerous capabilities like arbitrary code execution that would make this surface highly exploitable. - Ingestion points: Webhook endpoint
/api/webhooks-orders-create.tsand tracking API/api/track.ts. - Boundary markers: Encourages JSON schema validation (
validate(raw)) as seen inarchitecture.md. - Capability inventory: Capabilities are limited to outgoing network requests to analytics vendors.
- Sanitization: Implements server-side PII hashing as described in
architecture.md.
Audit Metadata