expo-migrate-module
Warn
Audited by Gen Agent Trust Hub on Aug 14, 2026
Risk Level: MEDIUMEXTERNAL_DOWNLOADSREMOTE_CODE_EXECUTIONCOMMAND_EXECUTION
Full Analysis
- [REMOTE_CODE_EXECUTION]: The skill instructs the user or agent to execute
npx --yes submit-expo-feedback@latest. This command downloads and runs a package from the NPM registry at runtime. Because the package is from an unverified author and not a trusted organization, it could execute arbitrary code on the system. - [COMMAND_EXECUTION]: The skill documentation includes instructions to use the GitHub CLI (
gh issue create --repo expo/expo) to report limitations. While it targets the official Expo repository, it grants the agent the ability to interact with external services and publish data to public repositories. - [INDIRECT_PROMPT_INJECTION]: The skill processes Swift, TypeScript, and JavaScript source code from the local repository to perform migrations. This creates an attack surface where malicious code within the repository could contain instructions that influence the agent's behavior. 1. Ingestion points: Swift module source files, TypeScript declarations, and JavaScript bindings located in the workspace (SKILL.md). 2. Boundary markers: None. The instructions do not specify the use of delimiters or warnings to ignore embedded instructions in the source code. 3. Capability inventory: File system read/write, shell command execution (
grep,find), and GitHub CLI interaction for issue creation. 4. Sanitization: The instructions do not define any sanitization, validation, or escaping logic for the ingested source code before it is processed.
Audit Metadata