enrichment-nyne

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

• Third-party content exposure detected (high risk: 0.78). The skill’s runtime calls Nyne enrichment/search endpoints via v1/proxy/orthogonal/run using user-supplied inputs like social_media_url/social_media_url and validate_keyword, which can cause the backend to fetch and return outsider-authored free text from public web/social pages into the agent’s context.