shopify

Pass

Audited by Gen Agent Trust Hub on Nov 11, 2026

Risk Level: SAFEINDIRECT_PROMPT_INJECTIONEXTERNAL_DOWNLOADSCOMMAND_EXECUTION
Full Analysis
  • [INDIRECT_PROMPT_INJECTION]: The skill ingests data from external Shopify records, such as orders, customers, and product metadata, creating a surface for indirect prompt injection.
  • Ingestion points: Data enters the agent's context through membrane action run and membrane request commands as described in SKILL.md.
  • Boundary markers: There are no explicit delimiters or instructions provided to the agent to ignore or sanitize embedded commands within the retrieved Shopify data.
  • Capability inventory: The skill possesses the capability to execute shell commands via the membrane CLI and perform network requests to the Shopify API.
  • Sanitization: No evidence of input validation or sanitization of retrieved external content is present in the instructions.
  • [EXTERNAL_DOWNLOADS]: The skill instructs the user to install the Membrane CLI from a public registry.
  • Evidence: npm install -g @membranehq/cli@latest and npx @membranehq/cli are used to set up the necessary environment.
  • Context: These are official tools provided by the skill's vendor for managing authentication and API interactions.
  • [COMMAND_EXECUTION]: The skill relies on executing the membrane CLI to perform all its functions.
  • Evidence: Numerous examples in SKILL.md use the membrane command to authenticate, connect to Shopify, and run actions.
Audit Metadata
Risk Level
SAFE
Analyzed
Nov 11, 2026, 05:48 AM