shopify

Pass

Audited by Gen Agent Trust Hub on Apr 8, 2026

Risk Level: SAFEPROMPT_INJECTION
Full Analysis
  • [PROMPT_INJECTION]: The skill processes store and customer data from the Shopify Admin API, which presents a surface for indirect prompt injection if the external data contains malicious instructions designed to influence the agent.
  • Ingestion points: Data is fetched from the Shopify Admin API in scripts/shopify_client.py and processed in scripts/analyze.py.
  • Boundary markers: Fetched data is presented to the agent without explicit delimiters or instructions to ignore embedded commands.
  • Capability inventory: The skill performs network read operations (Shopify API) and local file write operations (audit reports).
  • Sanitization: The scripts utilize standard JSON and CSV parsing; no content-based filtering for natural language instructions is applied to the fetched data.
  • [SAFE]: The skill implements security best practices by advising the use of environment variables for API credentials and including directory traversal checks in the report generation scripts.
Audit Metadata
Risk Level
SAFE
Analyzed
Apr 8, 2026, 06:55 PM