etoile

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

• Third-party content exposure detected (high risk: 0.90). The skill explicitly permits indexing "content" as a website URL or image URL in the Operation Checklist and references/etoile-api-reference.md (Indexing section), so the agent may ingest arbitrary public web content which could contain untrusted instructions that influence filtering, search results, or downstream actions like autoFilters.