bc-api-graphql

MEDIUM W011: Third-party content exposure detected (indirect prompt injection risk).

• Third-party content exposure detected (high risk: 0.90). The SKILL.md explicitly directs the agent to "Fetch live docs" (e.g., https://developer.bigcommerce.com/docs/storefront/graphql and web-searches) and to query arbitrary storefront endpoints (https://{store_domain}/graphql), meaning the agent will ingest public third-party site content that can change schema/auth behavior and thus materially influence its actions.