Uploaded June 2026 | Updated September 2026, 1 week ago

---

Explore how to evaluate threats from indirect prompt injection, such as data exfiltration and unintended actions. Discover system safeguards and security best practices for using App Intents and the Foundation Models framework, including mitigations such as user confirmations, secure prompt design, and authentication.

Explore related documentation, sample code, and more:
Security Overview: developer.apple.com/security
Explore prompt design & safety for on-device foundation models: developer.apple.com/videos/play/wwdc2025/248
Secure your app: threat modeling and anti-patterns: developer.apple.com/videos/play/wwdc2020/10189
Build agentic app experiences with the Foundation Models framework: developer.apple.com/videos/play/wwdc2026/242
Build intelligent Siri experiences with App Schemas: developer.apple.com/videos/play/wwdc2026/240
Explore advanced App Intents features for Siri and Apple Intelligence: developer.apple.com/videos/play/wwdc2026/343

More Apple Developer resources:
Video sessions: apple.co/VideoSessions
Documentation: apple.co/DeveloperDocs
Forums: apple.co/DeveloperForums
App: apple.co/DeveloperApp