find-endfield-data

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

• Third-party content exposure detected (high risk: 1.00). The SKILL.md explicitly directs the agent to fetch and interpret data and assets from public endpoints on https://endfield-assets.fffdan.com (e.g., /vfs/Table/, /table/{TableName}, /vfs/Bundle/search/{*query}), which are untrusted third‑party sources whose content the agent is expected to read and could therefore contain instructions that influence its behavior.