notion-research-documentation

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

• Third-party content exposure detected (high risk: 0.70). The skill's advanced-search documentation explicitly says searches can extend to connected third-party sources (see reference/advanced-search.md "Connected Sources" — Slack messages, Google Drive, GitHub issues/PRs, Jira), and the workflow fetches and synthesizes those results, meaning the agent will read and interpret user-generated or external content that could be untrusted.