bdistill-predict

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

• Third-party content exposure detected (high risk: 0.90). The skill's SKILL.md explicitly requires a "grounded" mode that will "search the web" and tag evidence as [web] (see the EXTRACT phase and example evidence entries with URL sources), so the agent fetches and interprets open/public third‑party content that can materially influence predictions.