nutmeg-compute

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

• Third-party content exposure detected (high risk: 0.70). The skill explicitly references fetching public data (e.g., "Understat: available via web scraping per match" in the Metric reference) and instructs the agent to process "API responses, web pages, downloaded files" as part of its workflow, so it will ingest untrusted third‑party web content that could influence computations or actions.