expo-gluestack

Pass

Audited by Gen Agent Trust Hub on Mar 21, 2026

Risk Level: SAFEPROMPT_INJECTIONEXTERNAL_DOWNLOADSCOMMAND_EXECUTION
Full Analysis
  • [PROMPT_INJECTION]: The skill instructs the agent to manage UI components by executing shell commands based on user input, specifically using the pattern 'npx gluestack-ui add [component-name]'. This creates a surface for indirect prompt injection.
  • Ingestion points: User requests for specific UI components as described in Section 3A of SKILL.md.
  • Boundary markers: The skill does not provide delimiters or instructions to the agent to treat user-provided component names strictly as data.
  • Capability inventory: The agent is empowered to execute terminal commands (npx) and modify the project structure.
  • Sanitization: There are no instructions provided to validate or sanitize the component names before they are interpolated into the shell command.
  • [EXTERNAL_DOWNLOADS]: The skill incorporates external guidance and best practices by referencing repositories from the official Expo organization and Callstack's incubator. These references are to well-known and reputable entities in the mobile development community.
  • [COMMAND_EXECUTION]: The workflow relies on several standard project initialization and configuration commands, such as 'npx create-expo-app' and 'npx gluestack-ui init'. These are typical and expected operations for setting up the development environment described in the skill.
Audit Metadata
Risk Level
SAFE
Analyzed
Mar 21, 2026, 07:49 AM