authentication
Pass
Audited by Gen Agent Trust Hub on Sep 11, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill defines authentication flows that ingest external data (identity tokens and authorization codes) from third-party providers.
- Ingestion points: Authentication credentials received via
ASAuthorizationAppleIDCredentialinSKILL.md. - Boundary markers: None defined to separate token data from agent instructions.
- Capability inventory: Network communication via
URLSessionand sensitive data storage via theKeychainAPI. - Sanitization: The skill provides clear instructions for server-side validation of JWTs using official public keys to prevent trust in client-side data.
Audit Metadata