expo-nativewind-theme
Pass
Audited by Gen Agent Trust Hub on Aug 25, 2026
Risk Level: SAFEEXTERNAL_DOWNLOADSCOMMAND_EXECUTION
Full Analysis
- [DATA_EXPOSURE_AND_EXFILTRATION]: The skill reads project configuration files such as
package.json,app.json,babel.config.js, andmetro.config.js. This information is used solely to verify the existing project environment and ensure compatibility with the NativeWind installation, which is a standard and expected operation for developer tooling. - [UNVERIFIABLE_DEPENDENCIES_AND_REMOTE_CODE_EXECUTION]: The skill triggers the installation of well-known libraries like
nativewind,sonner-native, and official Google Font packages. These installations are performed via thenpx expo installcommand, utilizing the project's default package manager and official registries, which is the recommended secure method for Expo dependency management. - [INDIRECT_PROMPT_INJECTION]: The skill establishes a surface for indirect prompt injection by reading local file content to determine project context. While this could theoretically allow malicious instructions in project files to influence the agent, it is a necessary feature for the tool's primary purpose.
- Ingestion points: Reads
package.json, root layout files, and configuration scripts from the user's local repository (SKILL.md). - Boundary markers: The instructions do not define explicit delimiters to separate ingested file data from system prompts.
- Capability inventory: The skill is authorized to install packages and write configuration code to the project file system (SKILL.md).
- Sanitization: No specific content filtering or sanitization logic is implemented for the ingested file data.
Audit Metadata