data-pipeline

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

• Third-party content exposure detected (high risk: 0.80). The SKILL.md explicitly defines extractors that fetch data from arbitrary REST/GraphQL URLs and external file sources (e.g., "rest_api: url", "graphql: url", "files: source: sftp/s3/google_drive", and saas connectors like Shopify/Stripe), which are untrusted third‑party sources whose content the skill ingests and uses in transformations and loads as part of the required workflow.