react-native-ai-skills

Pass

Audited by Gen Agent Trust Hub on Sep 14, 2026

Risk Level: SAFE
Full Analysis
  • [SAFE]: The skill provides setup guides for the @react-native-ai library ecosystem. All referenced packages such as @react-native-ai/apple, @react-native-ai/llama, and @react-native-ai/mlc are official vendor components. External links point to the vendor's official documentation at react-native-ai.dev and their GitHub repository at github.com/callstackincubator/ai.
  • [INDIRECT_PROMPT_INJECTION]: The skill facilitates the development of applications that process user-generated text through local LLMs. While this creates a surface for indirect prompt injection, it is the primary intended function of the tool. The instructions follow standard integration patterns for the Vercel AI SDK and on-device model management.
  • [COMMAND_EXECUTION]: The skill includes standard package management commands (npm add) and configuration instructions for React Native and Expo projects. These are necessary for the documented integration process and do not involve arbitrary or hidden command execution.
Audit Metadata
Risk Level
SAFE
Analyzed
Sep 14, 2026, 04:28 PM
Security Audit — agent-trust-hub — react-native-ai-skills