shopify-admin-agentic-organization-schema
Pass
Audited by Gen Agent Trust Hub on Jun 20, 2026
Risk Level: SAFEPROMPT_INJECTIONCOMMAND_EXECUTION
Full Analysis
- [PROMPT_INJECTION]: The skill represents a surface for indirect prompt injection by processing external data (shop metadata and user-supplied parameters) and interpolating it into Liquid templates.
- Ingestion points: The
shopquery results (name, email) and user-supplied parameters (same_as,logo_url) inSKILL.md. - Boundary markers: The skill instructions specify the use of
# BEGIN/ENDmarker blocks and comments within snippets to delimit the injected content. - Capability inventory: The
themeFilesUpsertmutation allows the agent to write persistent changes to theme files. - Sanitization: No explicit instructions for escaping or sanitizing the input data are provided before it is injected into the Liquid scripts.
- [COMMAND_EXECUTION]: The skill is authorized to perform state-changing mutations on the Shopify store's theme assets (
theme.liquidand snippets). While this is the primary purpose of the skill, it involves editing critical layout files. The risk is mitigated by the inclusion of a mandatorydry_runparameter and clear safety warnings in the documentation.
Audit Metadata