shopify-admin-agentic-crawler-access
Pass
Audited by Gen Agent Trust Hub on Jun 20, 2026
Risk Level: SAFECOMMAND_EXECUTIONPROMPT_INJECTION
Full Analysis
- [SAFE]: The skill performs intended Shopify administrative tasks using official toolkits. No malicious patterns or security risks were identified.
- [COMMAND_EXECUTION]: The skill uses the themeFilesUpsert mutation to modify store configuration files. This is the primary purpose of the skill and is protected by a dry_run parameter that is enabled by default.
- [PROMPT_INJECTION]: The skill includes instructions that mandate specific output formats for the agent. These are used for structured session tracking and do not attempt to bypass safety guidelines.
- [PROMPT_INJECTION]: The skill possesses an indirect prompt injection surface as it reads and processes external content from the Shopify store's theme files. 1. Ingestion points: Step 1 reads the content of templates/robots.txt.liquid via a GraphQL query. 2. Boundary markers: The skill does not use specific delimiters to isolate the retrieved file content from the agent's instructions during processing. 3. Capability inventory: The skill has the ability to write back to the theme via the themeFilesUpsert mutation. 4. Sanitization: No explicit sanitization or validation of the retrieved file content is performed before it is used to compute the new template.
Audit Metadata