styling-nativewind-v4-expo

Warn

Audited by Gen Agent Trust Hub on Feb 17, 2026

Risk Level: MEDIUMEXTERNAL_DOWNLOADSPROMPT_INJECTIONCOMMAND_EXECUTION
Full Analysis
  • [EXTERNAL_DOWNLOADS] (MEDIUM): The skill recommends the command npx rn-new --nativewind for new project initialization in references/expo-setup.md. This executes code from an unverified third-party package (rn-new) on the npm registry that is not associated with the defined list of trusted organizations.
  • [PROMPT_INJECTION] (LOW): The 'NativeWind v4 config audit' section in SKILL.md creates a surface for indirect prompt injection by instructing the agent to ingest and analyze arbitrary repository configuration files.
  • Ingestion points: Reads tailwind.config.js, babel.config.js, metro.config.js, app.json, and package.json.
  • Boundary markers: Absent; the prompt does not include instructions for the agent to ignore or delimit natural language commands that might be embedded in the audited files (e.g., within comments).
  • Capability inventory: The agent is empowered to generate code diffs and suggest terminal commands for the user to execute based on its analysis of these files.
  • Sanitization: Absent; the files are processed as raw text without validation or filtering.
  • [COMMAND_EXECUTION] (LOW): The skill guides the user and agent to execute several ecosystem-standard CLI commands, such as npx expo start --clear and npx tailwindcss, which involve external binary execution.
Audit Metadata
Risk Level
MEDIUM
Analyzed
Feb 17, 2026, 05:59 PM