notion

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

• Third-party content exposure detected (high risk: 0.75). Outsider-authored free text can enter the LLM via Notion page/block/database content that the skill retrieves at runtime (e.g., notion_search, notion_retrieve_page, notion_retrieve_block, notion_retrieve_database_content), where Notion content may be authored by people other than the operating user.

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

• Potentially malicious external URL detected (high risk: 0.90). The skill instructs the agent to run the ClawLink CLI via npx (npx @useclawlink/cli), which fetches and executes remote npm package code at runtime (see https://www.npmjs.com/package/@useclawlink/cli and https://claw-link.dev), so external code is executed and controls agent actions.