nby-notion-smart-categorize

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

• Third-party content exposure detected (low risk: 0.10). The skill reads Notion page contents and blocks via API and optionally fetches external URLs using WebFetch, both of which can contain outsider-authored text.

MEDIUM W012: Unverifiable external dependency detected (runtime URL that controls agent).

• Potentially malicious external URL detected (medium risk: 0.30). The skill uses Jina AI reader service (https://r.jina.ai/{LINK_URL}) at runtime to fetch page content, representing an unverified third-party operational dependency.