The Agent Skills Directory

[INDIRECT_PROMPT_INJECTION]: The skill processes untrusted user codebase files to generate migration plans, which presents an indirect prompt injection surface.
Ingestion points: The provided script scripts/analyze_react_stack.py reads content from all React component (.tsx) and test files within a user-specified project path to identify UI library usage.
Boundary markers: The skill does not define specific delimiters or instructions to ignore embedded prompts within the source code being analyzed.
Capability inventory: The skill performs local file read operations to analyze components and writes the results to a local JSON file (component_migration_plan.json).
Sanitization: No sanitization or escaping is performed on the code content during the analysis phase before the findings are presented to the agent for plan generation.

sgds-migration