matrixscan-ar-annotation-ios
Pass
Audited by Gen Agent Trust Hub on Sep 14, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill instructions direct the agent to analyze the user's project files to determine the development environment (e.g., searching for
import SwiftUIorBarcodeArView). This data ingestion is used solely to provide relevant code suggestions and correctly route the user's intent within the skill's scope. - [SAFE]: The skill emphasizes the use of official vendor documentation (docs.scandit.com) and verified code samples from the vendor's GitHub repository. These resources are appropriate for the skill's purpose and originate from a trusted source.
- [SAFE]: The functional constraints placed on the agent, such as instructions not to guess documentation URLs and to provide direct information rather than redirecting the user, are designed to ensure technical accuracy and improve user experience rather than to conceal malicious activity.
Audit Metadata