The Agent Skills Directory

[INDIRECT_PROMPT_INJECTION]: The skill is designed to ingest and process local source code files to perform migrations. This creates a surface for indirect prompt injection if the code being migrated contains adversarial instructions.
Ingestion points: Reads .ts and .tsx files from the project's source directory (e.g., src) to identify Tailwind class patterns.
Boundary markers: None identified; the skill does not explicitly use delimiters or instructions to ignore embedded prompts within the source code files.
Capability inventory: The skill has the capability to write/modify local files (implementing the migration) and execute a local auditing script (scripts/check-styles.mjs) using Node.js.
Sanitization: No explicit sanitization or filtering of the source code content is performed before the agent processes it for transformation logic.
[COMMAND_EXECUTION]: The skill executes an included Node.js script (scripts/check-styles.mjs) to validate styling rules. This script is a local utility provided by the author to perform static analysis on class names and does not perform network operations or access sensitive system files.
[DATA_EXPOSURE_AND_EXFILTRATION]: The skill reads project source code to fulfill its primary purpose. It does not contain hardcoded secrets, nor does it attempt to access sensitive configuration files (like .env or SSH keys) or transmit data to external domains.

tailwind-to-cva