react-expert
Pass
Audited by Gen Agent Trust Hub on Sep 28, 2026
Risk Level: SAFECOMMAND_EXECUTIONINDIRECT_PROMPT_INJECTIONEXTERNAL_DOWNLOADS
Full Analysis
- [COMMAND_EXECUTION]: The skill performs environment detection and code diagnostics using shell commands such as
grep,find,npm, andnpxto identify project structures and React patterns.- [EXTERNAL_DOWNLOADS]: The skill invokesnpxandnpm, which may download dependencies or tools from the official npm registry during analysis, linting, or testing.- [INDIRECT_PROMPT_INJECTION]: The skill analyzes local project files, which serves as an ingestion point for potentially untrusted data that could influence agent behavior. - Ingestion points: Source code files (
.jsx,.tsx) and project configuration files (package.json,next.config.js, etc.) read via diagnostic shell commands. - Boundary markers: The skill does not employ explicit delimiters to isolate file content from diagnostic instructions.
- Capability inventory: Shell command execution for diagnostics (
grep,find,wc) and package management tools (npm,npx). - Sanitization: No sanitization is performed on the data retrieved from project files before it is processed by the agent.
Audit Metadata