app-intents-specialist
Pass
Audited by Gen Agent Trust Hub on Oct 13, 2026
Risk Level: SAFE
Full Analysis
- [SAFE]: The skill serves as a technical reference library for Apple's App Intents. It contains extensive documentation on implementation details such as persistence, parameter resolution, and execution models.
- [SAFE]: No evidence of prompt injection or attempts to bypass safety filters was detected. The instructions provided in SKILL.md and apple/guide.md are standard operational guidelines for a coding assistant to prioritize provided context over base model training.
- [SAFE]: No obfuscation techniques (Base64, zero-width characters, homoglyphs) were found in the instructions, documentation, or code snippets.
- [SAFE]: External links are limited to official Apple developer domains (developer.apple.com), which are recognized as trusted sources.
- [SAFE]: The skill does not involve remote code execution, package installations, or privilege escalation. It specifically instructs the agent to use only tools available in the current session and to avoid inventing tool schemas.
- [SAFE]: The inclusion of a UPSTREAM.json file with SHA-256 digests for all documentation files demonstrates a commitment to content integrity and supply chain transparency.
Audit Metadata