shopify-hello-world
Pass
Audited by Gen Agent Trust Hub on Sep 9, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill ingests untrusted product data (titles, descriptions, and variant details) from the Shopify Admin API, which could theoretically contain malicious instructions.
- Ingestion points: Product and shop metadata are fetched via GraphQL and REST queries in
references/hello-world-script.mdandreferences/graphql-mutation-and-rest-examples.md. - Boundary markers: The implementation does not utilize specific delimiters or instructions to the agent to disregard potential prompts embedded within the retrieved product data.
- Capability inventory: The skill execution environment permits file operations and shell command execution through Node.js and npm-related tools.
- Sanitization: There is no evidence of sanitization, escaping, or validation of the data retrieved from the Shopify API before it is processed or output to the console.
Audit Metadata