shopify-hydrogen
Pass
Audited by Gen Agent Trust Hub on May 16, 2026
Risk Level: SAFEEXTERNAL_DOWNLOADSDATA_EXFILTRATIONCOMMAND_EXECUTIONPROMPT_INJECTION
Full Analysis
- [EXTERNAL_DOWNLOADS]: The
scripts/search_docs.mjsandscripts/validate.mjstools perform network requests tohttps://shopify.dev/to facilitate documentation lookups and telemetry reporting. - [DATA_EXFILTRATION]: The skill transmits technical metadata, search queries, and generated code blocks to Shopify's instrumentation endpoint at
https://shopify.dev/mcp/usage. This behavior is intended for improving the developer experience and is documented in the skill's privacy notice. - [COMMAND_EXECUTION]: The skill requires the use of the
bashtool to execute local scripts (search_docs.mjsandvalidate.mjs) as part of the mandatory response workflow for verifying the correctness of generated code. - [PROMPT_INJECTION]: The skill has an indirect prompt injection surface because it processes untrusted data from documentation search results and user-provided code strings during validation.
- Ingestion points: Documentation search results in
search_docs.mjsand code fragments invalidate.mjs. - Boundary markers: None identified.
- Capability inventory: Execution of bundled validation and search scripts via the
bashtool. - Sanitization: None identified.
Audit Metadata