evernote-sdk-patterns

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

• Third-party content exposure detected (high risk: 0.90). This skill's implementation guide (references/implementation-guide.md) shows it fetching and reading user-generated Evernote content via noteStore.findNotesMetadata, noteStore.getNote, and related APIs and then acting on that content (e.g., tagging, moving, deleting notes), so untrusted third-party note content could indirectly inject instructions that affect agent behavior.