acquire

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

• Third-party content exposure detected (high risk: 0.90). The SKILL.md explicitly instructs fetching and ingesting public third-party data (e.g., the raw GitHub URL for StatsBomb events and the "Self-discovery" step that tells the agent to "search the web" for data sources), so untrusted web content could be read and influence source selection and downstream actions.