shopify-orders
Pass
Audited by Gen Agent Trust Hub on Sep 17, 2026
Risk Level: SAFEEXTERNAL_DOWNLOADSINDIRECT_PROMPT_INJECTION
Full Analysis
- [EXTERNAL_DOWNLOADS]: The skill instructs the agent to fetch live technical documentation from Shopify's official developer portal (shopify.dev) using WebSearch and WebFetch tools. This is a standard and safe practice for retrieving up-to-date API specifications from a well-known service.
- [INDIRECT_PROMPT_INJECTION]: The skill uses web retrieval tools to ingest content from external websites into the agent's context. This creates a potential surface for indirect prompt injection where instructions embedded in external content could influence the agent.
- Ingestion points: WebSearch and WebFetch operations described in SKILL.md for retrieving API documentation.
- Boundary markers: None provided in the instructions to help the agent distinguish between its core instructions and the fetched data.
- Capability inventory: The skill is configured within an environment that includes file modification (Write, Edit) and command execution (Bash) capabilities.
- Sanitization: The instructions do not specify any validation or sanitization protocols for the content retrieved from external sources.
Audit Metadata