background-processing
Pass
Audited by Gen Agent Trust Hub on Aug 23, 2026
Risk Level: SAFEPROMPT_INJECTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill documents the processing of data from push notifications, which is an ingestion point for untrusted external data. 1. Ingestion points: The notification payload (userInfo) in the didReceiveRemoteNotification method in SKILL.md. 2. Boundary markers: Absent. 3. Capability inventory: Network access via URLSession and file system access via FileManager. 4. Sanitization: Absent.
- [SAFE]: The skill provides standard documentation for iOS development. No signs of obfuscation, unauthorized persistence, or data exfiltration were detected. The use of private APIs is restricted to debugging contexts on physical devices as per standard developer workflows.
Audit Metadata