react-doctor

Warn

Audited by Gen Agent Trust Hub on Apr 12, 2026

Risk Level: MEDIUMEXTERNAL_DOWNLOADSREMOTE_CODE_EXECUTIONCOMMAND_EXECUTIONPROMPT_INJECTION
Full Analysis
  • [EXTERNAL_DOWNLOADS]: The skill uses npx with the -y flag to automatically download the react-doctor package from the public NPM registry. The use of the @latest tag ensures the most recent version is fetched, meaning the code executed can be modified at the source without notice.
  • [REMOTE_CODE_EXECUTION]: The downloaded package is executed immediately using the Bash tool. This allows third-party code to run within the agent's environment with the same privileges as the agent.
  • [COMMAND_EXECUTION]: User-supplied arguments are passed directly into a shell command via $ARGUMENTS. This presents a risk of command injection if the inputs are not properly sanitized by the platform.
  • [PROMPT_INJECTION]: The skill reads content from React files which provides an indirect prompt injection surface. Ingestion points: Files matching **/*.tsx and **/*.jsx. Boundary markers: None present. Capability inventory: Includes shell execution, file reading, and remote package installation. Sanitization: No validation or escaping of file content is performed.
Audit Metadata
Risk Level
MEDIUM
Analyzed
Apr 12, 2026, 11:56 AM
Security Audit — agent-trust-hub — react-doctor