react-doctor

Pass

Audited by Gen Agent Trust Hub on Sep 21, 2026

Risk Level: SAFEEXTERNAL_DOWNLOADSCOMMAND_EXECUTIONINDIRECT_PROMPT_INJECTION
Full Analysis
  • [EXTERNAL_DOWNLOADS]: The skill recommends using npx -y react-doctor@latest, which downloads and executes code from the NPM registry.
  • [COMMAND_EXECUTION]: The instruction contains a shell command (npx -y react-doctor@latest . --verbose --diff) intended for execution in the user's environment.
  • [INDIRECT_PROMPT_INJECTION]: The tool is designed to scan project codebases, which are external, untrusted inputs. Malicious content within the scanned files could potentially target the agent's interpretation of the tool's diagnostic output.
  • Ingestion points: Project files in the directory passed as an argument (.) to the scanner.
  • Boundary markers: None identified in the skill instructions to separate project data from diagnostic output.
  • Capability inventory: The skill executes shell commands via npx.
  • Sanitization: No sanitization or validation of the codebase content is performed before processing.
Audit Metadata
Risk Level
SAFE
Analyzed
Sep 21, 2026, 04:15 PM