ecommerce-shopify-store-query
Pass
Audited by Gen Agent Trust Hub on Sep 14, 2026
Risk Level: SAFECOMMAND_EXECUTIONINDIRECT_PROMPT_INJECTION
Full Analysis
- [COMMAND_EXECUTION]: The skill includes a functional Python script,
scripts/shopify_store_query.py, intended to be executed by the agent to perform network requests, manage a local result cache, and save research data to the filesystem. - [INDIRECT_PROMPT_INJECTION]: The skill ingests and processes data from an external Shopify store query API, which represents a potential surface for indirect prompt injection if store-provided content contains malicious instructions.
- Ingestion points: Data is fetched from a remote gateway via the
call_apimethod inscripts/shopify_store_query.py, retrieving fields like store names, domains, and social media metadata. - Boundary markers: The script's output to the agent's context does not utilize specific delimiters or instructions to treat the external API content as untrusted.
- Capability inventory: The skill can execute local Python scripts, perform network POST operations, and write persistent JSON files to the local
nexscopedirectory. - Sanitization: The script does not perform sanitization or filtering on the retrieved API data before displaying it or saving it to disk.
Audit Metadata