oban-essentials

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

• Third-party content exposure detected (high risk: 0.80). The SKILL.md's "Error Handling" section includes a required worker example that calls HTTPClient.get(url) on a job-provided URL and then processes the fetched body (process(body)), which clearly shows ingestion and interpretation of arbitrary third-party web content that could influence job behavior.