The Agent Skills Directory

[PROMPT_INJECTION]: The skill is susceptible to indirect prompt injection as it is designed to ingest and process external React source code for modernization.
Ingestion points: Ingests React application codebases through the input_1 parameter and referenced project files.
Boundary markers: Absent. There are no instructions to use delimiters or warnings to ignore instructions embedded within the source code being analyzed.
Capability inventory: The skill utilizes shell command execution via npx and jscodeshift to perform code transformations.
Sanitization: Absent. No validation or sanitization of the input source code is performed before processing it through transformation tools.
[COMMAND_EXECUTION]: The skill instructs the agent to execute shell commands to automate code refactoring.
Evidence: Uses npm install -g jscodeshift, npx react-codeshift, and npx codemod to apply transformations to the codebase.
Context: These are standard developer tools for React migrations, but they provide a mechanism for code execution on the host environment.

react-modernization