cross-device-design
Pass
Audited by Gen Agent Trust Hub on Sep 27, 2026
Risk Level: SAFEEXTERNAL_DOWNLOADS
Full Analysis
- [SAFE]: The skill consists entirely of instructional text and design guidelines. No command execution, script generation, or persistence mechanisms were detected.
- [EXTERNAL_DOWNLOADS]: The skill contains references to official developer documentation from Apple (developer.apple.com), Google (developer.android.com), and Microsoft (learn.microsoft.com). These are trusted, well-known sources used for research and technical guidance.
- [PROMPT_INJECTION]: No attempts to override system instructions, bypass safety filters, or extract system prompts were found. The instructional language is consistent with the skill's stated purpose of cross-device design.
- [INDIRECT_PROMPT_INJECTION]: The skill does not ingest untrusted data or automate interactions with external services that could lead to indirect injection. It serves as a framework for the agent's reasoning process.
Audit Metadata