api-graphql
Pass
Audited by Gen Agent Trust Hub on Sep 27, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill ingests data from external Shopify store resources which presents a surface for indirect prompt injection.\n
- Ingestion points: GraphQL query responses for products, customers, and orders as defined in
SKILL.mdandreferences/QUERY_EXAMPLES.md.\n - Boundary markers: The skill does not provide delimiters or specific instructions to the agent to treat data from the API as untrusted or separate from instructions.\n
- Capability inventory: The skill includes extensive write capabilities via mutations (e.g.,
productCreate,customerCreate,metafieldsSet) allowing modification of store data based on ingested content.\n - Sanitization: No sanitization, validation, or escaping of fetched API data is described in the implementation examples.
Audit Metadata