shopify-admin-file-storage-audit
Pass
Audited by Gen Agent Trust Hub on Jun 20, 2026
Risk Level: SAFE
Full Analysis
- [SAFE]: The skill is restricted to read-only operations as declared in the metadata and reinforced by the workflow steps. It only utilizes the
shopify-adminandshopify-admin-executiontoolkits for standard GraphQL queries. - [SAFE]: No evidence of data exfiltration or unauthorized network communication was found. Data remains within the agent's context for report generation.
- [PROMPT_INJECTION]: The skill ingests untrusted content from Shopify page and article bodies to scan for URL references. While this represents an indirect prompt injection surface (Category 8), the risk is negligible as the skill lacks capabilities to execute shell commands, perform network requests to external domains, or modify store data.
- Ingestion points:
pages:queryandarticles:query(body field). - Boundary markers: None specified in the extraction logic.
- Capability inventory: Read-only GraphQL queries, local cross-referencing, and CSV file creation.
- Sanitization: Not explicitly defined, though the logic is limited to URL pattern matching.
- [SAFE]: The skill does not use any obfuscation, dynamic code execution, or external dependencies. It relies entirely on the host platform's Shopify integration.
Audit Metadata