list-builder

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

• Third-party content exposure detected (high risk: 0.80). This skill explicitly instructs the agent to research and expand lists using public third‑party sources (e.g., "Kiwix/Wikipedia" category pages and list articles) and to ingest those research sources as part of its workflow, exposing it to untrusted user‑generated web content.