query

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 the agent to fetch and parse a Dora instance's Swagger page via WebFetch at {base_url}/api/swagger/index.html (Dora
• Beacon Chain Explorer section), which causes the agent to read arbitrary third‑party API documentation and use discovered endpoints to drive subsequent actions.