hydrogen-cookbooks

Pass

Audited by Gen Agent Trust Hub on Apr 9, 2026

Risk Level: SAFECOMMAND_EXECUTIONEXTERNAL_DOWNLOADS
Full Analysis
  • [COMMAND_EXECUTION]: The SKILL.md file contains instructions to execute local scripts (scripts/search_shopify_docs.mjs and scripts/search_weaverse_docs.mjs) for documentation search purposes. These are part of the skill's utility tooling.
  • [EXTERNAL_DOWNLOADS]: The weaverse-hydrogen-integration.md reference guide instructs users to install the @weaverse/hydrogen package via standard package managers. This is a legitimate dependency provided by the vendor for the described integration.
  • [DATA_EXFILTRATION]: In customer-account-api.md, the skill describes using the Shopify Hydrogen CLI's tunnel feature (--customer-account-push__unstable) to expose the local development server to a public domain (tryhydrogen.dev). This is a standard and documented Shopify development workflow required for testing Customer Account API callbacks.
  • [PROMPT_INJECTION]: Several reference files (e.g., bundles.md, combined-listings.md) use structural headers like <user_queries> and instructional framing ("This prompt describes how to implement...") to guide the AI's response behavior. These are standard patterns for cookbook-style skills and do not contain malicious bypass instructions.
Audit Metadata
Risk Level
SAFE
Analyzed
Apr 9, 2026, 04:54 AM