bbc-skill-tool

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

• Third-party content exposure detected (high risk: 0.90). The skill explicitly instructs the agent to fetch and ingest open/public third-party content (e.g., update_answer.assistant.scrapeUrl in references/advanced-patterns.md, add_http endpoints, and public media URLs) to populate the AI knowledge base and drive responses, so untrusted web content can directly influence assistant behavior and tool calls.