shopify-hydrogen
Pass
Audited by Gen Agent Trust Hub on Nov 13, 2026
Risk Level: SAFEEXTERNAL_DOWNLOADSCOMMAND_EXECUTIONINDIRECT_PROMPT_INJECTION
Full Analysis
- [EXTERNAL_DOWNLOADS]: The skill includes scripts (scripts/search_shopify_docs.mjs, scripts/get_weaverse_page.mjs, scripts/search_weaverse_docs.mjs) that fetch documentation content from external domains including shopify.dev and weaverse.io. These downloads are performed to provide the agent with up-to-date API references and guides.
- [COMMAND_EXECUTION]: The script scripts/check_docs_helpers.mjs uses node:child_process.spawnSync to execute local scripts within the skill folder. This is used for boundary checking and validating the documentation helpers.
- [INDIRECT_PROMPT_INJECTION]: The documentation search functionality creates an ingestion surface for external content. Content fetched from shopify.dev and weaverse.io is provided to the agent, which could potentially contain instructions that influence the agent's behavior.
- Ingestion points: scripts/search_shopify_docs.mjs (Shopify API docs), scripts/get_weaverse_page.mjs (Weaverse doc pages), and scripts/search_weaverse_docs.mjs (Weaverse search results).
- Boundary markers: The scripts do not implement explicit delimiters or instructions to ignore embedded commands within the fetched documentation text.
- Capability inventory: The agent uses the ingested data to generate code snippets, provide setup instructions, and explain Shopify Hydrogen concepts. No dangerous capabilities (like file writing or subprocess execution) are directly triggered by the ingested text.
- Sanitization: scripts/get_weaverse_page.mjs implements strict regex validation (DOC_PATH) on the input path to prevent directory traversal or remote command injection, but does not sanitize the content returned by the API.
Audit Metadata