expo-data-fetching
Pass
Audited by Gen Agent Trust Hub on Oct 2, 2026
Risk Level: SAFEREMOTE_CODE_EXECUTIONCOMMAND_EXECUTIONINDIRECT_PROMPT_INJECTION
Full Analysis
- [REMOTE_CODE_EXECUTION]: The skill instructs the agent to report errors using
npx --yes submit-expo-feedback@latest, which involves downloading and executing code from the NPM registry. The package is identified as a vendor-provided utility. - [COMMAND_EXECUTION]: The feedback command incorporates a user-input placeholder (
<actionable feedback>). If an agent uses a shell tool to execute this without proper sanitization, it could be susceptible to command injection via shell metacharacters in the feedback text. - [INDIRECT_PROMPT_INJECTION]: The feedback mechanism establishes a potential attack surface where untrusted user input is passed to a command execution context.
- Ingestion points: User feedback placeholder in the feedback report command in
SKILL.md. - Boundary markers: None provided to encapsulate or escape the user input within the command string.
- Capability inventory: Shell execution capabilities via
npx. - Sanitization: No guidance is provided for sanitizing the feedback input before it is used in the shell command.
Audit Metadata