expo-uniwind-theme
Pass
Audited by Gen Agent Trust Hub on Sep 1, 2026
Risk Level: SAFEEXTERNAL_DOWNLOADSCOMMAND_EXECUTIONINDIRECT_PROMPT_INJECTION
Full Analysis
- [EXTERNAL_DOWNLOADS]: The skill references and fetches documentation from official product websites and public code repositories. These include documentation from
docs.uniwind.devand thesonner-native-toastsrepository on GitHub. These references are used for developer guidance and library integration.- [COMMAND_EXECUTION]: The skill instructs the agent to execute shell commands for project inspection and package management. Specifically, it uses the project's default package manager (e.g., npm, yarn, or pnpm) to installuniwind,tailwindcss, andsonner-native. It also reads local configuration files such aspackage.json,metro.config.js, and Expo configuration files to determine the project state.- [INDIRECT_PROMPT_INJECTION]: The skill processes content from the user's project files, creating a potential attack surface where instructions embedded in project data could influence the agent's behavior. - Ingestion points: The agent reads
package.json, root layout files, and Metro configurations from the local file system. - Boundary markers: No specific delimiters or "ignore instructions" warnings are utilized when processing these files.
- Capability inventory: The agent has the capability to execute shell commands for package installation and modify application source code.
- Sanitization: No explicit sanitization or validation of the ingested file content is mentioned.
Audit Metadata