react-native-design
Pass
Audited by Gen Agent Trust Hub on Oct 16, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [SAFE]: The skill provides architectural guidelines and best practices for creating production-grade React Native UI. It encourages the use of established, well-known libraries such as
styled-components,nativewind, andexpo-reanimated, which are industry standards. - [INDIRECT_PROMPT_INJECTION]: The skill contains instructions for the agent to inspect and audit existing project configuration files (e.g.,
package.json,tailwind.config.js,theme.ts) and screen source code to adapt its styling suggestions. This established ingestion surface is susceptible to indirect prompt injection if those project files contain adversarial content. - Ingestion points: Project metadata and source files (SKILL.md, lines 439-467).
- Boundary markers: The instructions do not specify the use of delimiters or 'ignore' markers when processing the contents of these files.
- Capability inventory: The skill allows the agent to read local project files and generate new application code based on that context.
- Sanitization: No sanitization or validation of the content read from the project files is defined in the instructions.
Audit Metadata