apple-foundation-models-production
Pass
Audited by Gen Agent Trust Hub on Aug 31, 2026
Risk Level: SAFENO_CODE
Full Analysis
- [SAFE]: The skill consists entirely of markdown documentation and engineering guidelines. No executable scripts, binaries, or automated tasks are included in the skill files.
- [SAFE]: The instructions promote defensive programming practices for AI integration, specifically mandating the use of opaque identifiers for citations, deterministic validation of model output, and strict privacy controls for session data and attachments.
- [SAFE]: All referenced sources are official Apple developer documentation accessed via the Xcode toolchain. No suspicious external dependencies, remote code downloads, or obfuscated URLs were identified.
- [SAFE]: The skill explicitly includes measures to test and mitigate prompt injection and instruction poisoning in external data, demonstrating a security-conscious design.
Audit Metadata