app-clips

Pass

Audited by Gen Agent Trust Hub on Aug 23, 2026

Risk Level: SAFEPROMPT_INJECTION
Full Analysis
  • [PROMPT_INJECTION]: The skill identifies a potential surface for indirect prompt injection through the processing of untrusted external data from invocation URLs.
  • Ingestion points: The NSUserActivity.webpageURL property is consumed and parsed in the WalletClip struct and ClipRoute enum within SKILL.md.
  • Boundary markers: Explicit delimiters or boundary markers for the URL payload are not implemented in the provided Swift code example.
  • Capability inventory: The skill documents the use of StoreKit for purchases, PassKit for Apple Pay, Core NFC for physical tag interaction, and local notifications.
  • Sanitization: The skill provides explicit developer instructions to validate URLs against the AASA, treat query parameters as untrusted input, and verify sensitive actions like financial transactions on the server side.
Audit Metadata
Risk Level
SAFE
Analyzed
Aug 23, 2026, 09:00 PM
Security Audit — agent-trust-hub — app-clips