react-doctor
Pass
Audited by Gen Agent Trust Hub on Apr 6, 2026
Risk Level: SAFEEXTERNAL_DOWNLOADSCOMMAND_EXECUTIONPROMPT_INJECTION
Full Analysis
- [COMMAND_EXECUTION]: The skill instructs the agent to run
npx -y react-doctor@latest . --verbose. This executes a shell command that runs a third-party utility with full access to the project's source code and file system. - [EXTERNAL_DOWNLOADS]: The use of
npxat runtime fetches thereact-doctorpackage from the public NPM registry. The use of the@latesttag ensures the most recent version is used but bypasses version pinning, which can be a risk if the package is compromised. - [PROMPT_INJECTION]: The skill is susceptible to indirect prompt injection because it processes untrusted codebase data.
- Ingestion points: The tool scans the entire codebase (current directory
.) as specified in SKILL.md. - Boundary markers: None are used to separate codebase content from the agent's instructions.
- Capability inventory: The skill possesses command execution capabilities via
npxin SKILL.md. - Sanitization: There is no evidence of sanitization or filtering of the codebase content before it is processed by the diagnostic tool.
Audit Metadata