notion-hardened

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 and SAFETY.md explicitly show the agent calling Notion API endpoints (e.g., POST /v1/search, GET /v1/pages/{page_id}, GET /v1/blocks/{page_id}/children) to fetch user-generated Notion page and block content which the agent is expected to read and act on (e.g., using page content to draft emails or modify pages), so untrusted third-party content can materially influence actions and enable indirect prompt injection.