notion

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

• Third-party content exposure detected (medium risk: 0.65). The skill’s runtime Notion API calls (e.g., GET /v1/blocks/{page_id}/children and POST /v1/data_sources/{data_source_id}/query) can ingest page/block text authored by other people into the agent’s LLM context, which is outsider-authored free text.