expo-gluestack-setup

MEDIUM W011: Third-party content exposure detected (indirect prompt injection risk).

• Third-party content exposure detected (high risk: 0.80). The skill explicitly instructs the agent to read and act on content from public third-party sources—specifically the gluestack.io documentation and the gluestack/gluestack-ui GitHub repository (including using the GitHub Contents API to enumerate and copy files)—and uses that fetched content to decide package versions, copy provider/components, and run commands, so external content can materially influence tool actions.

MEDIUM W012: Unverifiable external dependency detected (runtime URL that controls agent).

• Potentially malicious external URL detected (high risk: 1.00). The skill explicitly instructs the agent at runtime to fetch and copy official provider/component source from GitHub (e.g. https://github.com/gluestack/gluestack-ui and the GitHub Contents API endpoint gh api repos/gluestack/gluestack-ui/contents/?ref=), which pulls remote code that the skill requires and will be executed as part of the target app—meeting the criteria for a runtime external dependency that can execute remote code.