shopify-payments-apps
Pass
Audited by Gen Agent Trust Hub on May 15, 2026
Risk Level: SAFEEXTERNAL_DOWNLOADSDATA_EXFILTRATIONPROMPT_INJECTIONCOMMAND_EXECUTION
Full Analysis
- [EXTERNAL_DOWNLOADS]: The
scripts/search_docs.mjsscript performs network requests tohttps://shopify.dev/assistant/searchto retrieve API documentation and code examples. This is an expected functional requirement that utilizes the vendor's official documentation endpoint. - [DATA_EXFILTRATION]: The skill transmits anonymized telemetry data (including model names and client identifiers) to
https://shopify.dev/mcp/usage. This activity is explicitly disclosed in the skill's privacy notice and is directed to the vendor's own infrastructure for service improvement. - [COMMAND_EXECUTION]: The skill utilizes a
bashtool to execute local utility scripts (search_docs.mjsandvalidate.mjs) for documentation retrieval and syntax checking. These scripts use standard Node.js APIs and do not exhibit suspicious behavior. - [PROMPT_INJECTION]: The skill processes external content from the Shopify documentation API, representing a surface for indirect prompt injection.
- Ingestion points: Documentation search results from
scripts/search_docs.mjsare incorporated into the agent's context. - Boundary markers: No explicit delimiters or boundary markers are defined in the instructions for the search results.
- Capability inventory: The agent has access to a
bashtool for local script execution. - Sanitization: The skill does not explicitly describe sanitization or filtering of the retrieved API content before processing.
Audit Metadata