software-mansion-best-practices
Pass
Audited by Gen Agent Trust Hub on Apr 8, 2026
Risk Level: SAFE
Full Analysis
- [SAFE]: The skill serves as a documentation repository for React Native development. No malicious code, obfuscation, or unauthorized data access patterns were detected.
- [EXTERNAL_DOWNLOADS]: The skill provides instructions and code examples for downloading AI models and dependencies from official Software Mansion sources (swmansion.com, GitHub, HuggingFace). These resources are well-known and consistent with the skill's stated purpose.
- [DATA_EXFILTRATION]: Documents the use of Radon IDE MCP tools which allow developers to inspect application logs, network traffic, and UI states. These tools include security features such as the automatic redaction of sensitive HTTP headers (e.g., tokens, secrets, credentials).
- [PROMPT_INJECTION]: Documentation for on-device AI includes best practices for processing user input and generating structured output. These patterns are standard for building AI-integrated features and do not contain instructions to bypass safety filters or override agent behavior.
- [SAFE]: Standard development operations mentioned, such as
pod install,npm install, and modifyingInfo.plist, are essential steps for React Native development and are documented neutrally.
Audit Metadata