order-lookup-and-summary
Pass
Audited by Gen Agent Trust Hub on Apr 11, 2026
Risk Level: SAFECOMMAND_EXECUTIONPROMPT_INJECTIONNO_CODE
Full Analysis
- [SAFE]: The skill performs legitimate administrative operations within the Shopify ecosystem. It uses standard GraphQL queries and follows documented Shopify CLI authentication procedures.
- [COMMAND_EXECUTION]: The prerequisites section references the
shopify auth logincommand, which is the official method for establishing an authenticated session with the Shopify platform. - [PROMPT_INJECTION]: The skill is susceptible to indirect prompt injection because it ingests untrusted data from an external source (Shopify API).
- Ingestion points: Data fields from the Shopify
ordersquery, including order notes, tags, and line item titles, are processed and displayed to the user. - Boundary markers: No explicit delimiters or instructions are used to separate retrieved data from the agent's instructions.
- Capability inventory: The skill is strictly read-only and lacks capabilities for file-system access, network exfiltration, or secondary command execution.
- Sanitization: No sanitization or escaping is applied to the retrieved data before it is formatted for output. The risk is assessed as low given the skill's lack of destructive or executable capabilities.
- [NO_CODE]: This skill contains only markdown instructions and a GraphQL query definition in the SKILL.md file; no scripts, binaries, or external code dependencies are included.
Audit Metadata