react-refactor
Pass
Audited by Gen Agent Trust Hub on Sep 8, 2026
Risk Level: SAFECOMMAND_EXECUTIONEXTERNAL_DOWNLOADSINDIRECT_PROMPT_INJECTION
Full Analysis
- [COMMAND_EXECUTION]: The skill instructs the agent to use standard Unix utilities such as
find,grep,wc,sort, andheadfor project structure analysis, including locating monolith components and files lacking test coverage. - [EXTERNAL_DOWNLOADS]: Recommends running well-known development tools using
bunx, specificallyvite-bundle-visualizer,ts-prune, andknip, for bundle analysis and identifying unused exports or dependencies. - [INDIRECT_PROMPT_INJECTION]: The skill is designed to analyze and refactor existing codebase files, creating a potential surface for indirect prompt injection from untrusted content within those files.
- Ingestion points: The agent reads
.tsxsource files in thesrcdirectory during its analysis and migration steps. - Boundary markers: No specific delimiters or instructions to ignore embedded prompts within the codebase are provided.
- Capability inventory: The skill involves shell command execution (
find,grep,bunx) and file writing operations. - Sanitization: The instructions do not define a process for sanitizing or validating the content of the source files before processing.
Audit Metadata