notion

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

• Third-party content exposure detected (high risk: 0.90). The skill explicitly fetches and reads user-generated Notion content via the Notion API (e.g., POST /v1/search and GET /v1/blocks/{page_id}/children to get page/block content) and the SKILL.md shows workflows where the agent reads and then creates/updates pages, so untrusted third-party content could influence actions.