The Agent Skills Directory

[PROMPT_INJECTION]: The skill is designed to ingest and analyze external TypeScript source code for refactoring and review. This creates a surface for indirect prompt injection, where an attacker could embed malicious instructions in the target source files to influence the agent's behavior.
Ingestion points: Processes user-provided TypeScript source files throughout the project directory (e.g., during refactoring tasks).
Boundary markers: The skill instructions do not prescribe the use of delimiters or specific warnings to ignore instructions embedded within the code data being processed.
Capability inventory: As a tool for coding assistants, the agent utilizing this skill likely has access to file-system operations and terminal execution capabilities.
Sanitization: No logic is provided to sanitize, escape, or validate the content of the external code files before processing.
[NO_CODE]: The skill is composed strictly of markdown documentation and metadata files. It does not include any executable scripts (e.g., .js, .py) or binaries.

typescript-refactor