The Agent Skills Directory

[DYNAMIC_EXECUTION]: The skill dynamically calculates the path to a required toolkit (TOOLKIT_DIR) and executes scripts (setup.sh) and TypeScript files (ast-tool.ts) using bash and npx tsx based on these computed paths.
[INDIRECT_PROMPT_INJECTION]: The skill ingests untrusted data from the codebase being analyzed (routes, components, dependencies, and configuration files) to generate a migration assessment report, which creates a surface for indirect prompt injection.
Ingestion points: Files within the user-provided pagesDir, srcDir, packageJsonPath, and nextConfigPath are processed by an AST tool.
Boundary markers: The skill does not explicitly define delimiters or instructions to ignore embedded prompts within the source code being analyzed.
Capability inventory: The skill has the capability to read project source files and write assessment reports to the filesystem (.migration/ directory).
Sanitization: There is no evidence of sanitization or filtering of the content extracted from the codebase before it is used to generate the final assessment report.

migration-assessment