expo-overview

Pass

Audited by Gen Agent Trust Hub on Oct 5, 2026

Risk Level: SAFECOMMAND_EXECUTIONEXTERNAL_DOWNLOADSDATA_EXFILTRATIONINDIRECT_PROMPT_INJECTION
Full Analysis
  • [INDIRECT_PROMPT_INJECTION]: The skill processes external documents such as PRDs, requests, and specifications to determine routing and setup behavior. It lacks explicit boundary markers or sanitization procedures to prevent instructions embedded within these inputs from influencing agent operations.
  • Ingestion points: SKILL.md references reading user goals from requests, PRDs, or specs.
  • Boundary markers: None observed.
  • Capability inventory: Shell command execution via npx and eas (SKILL.md).
  • Sanitization: None observed.
  • [COMMAND_EXECUTION]: The instructions direct the agent to run various CLI tools, including npx, eas, and create-expo-app, for authentication, project initialization, and package installation.
  • Evidence: Commands such as npx create-expo-app@latest, npx expo install <pkg>, eas whoami, eas login, and eas init are listed as standard setup steps in SKILL.md.
  • [EXTERNAL_DOWNLOADS]: The skill triggers the download and execution of packages from the NPM registry at runtime via the npx command.
  • Evidence: npx create-expo-app@latest and npx --yes submit-expo-feedback@latest are used for project scaffolding and feedback submission in SKILL.md.
  • [DATA_EXFILTRATION]: A feedback mechanism is provided which allows for the transmission of text data from the agent's context to an external destination.
  • Evidence: The submit-expo-feedback command in SKILL.md transmits user-supplied feedback strings to an external service using a CLI utility.
Audit Metadata
Risk Level
SAFE
Analyzed
Oct 5, 2026, 09:27 PM