The Agent Skills Directory

[COMMAND_EXECUTION] (SAFE): The skill utilizes the Bash tool to execute npm run typecheck. This is a standard and expected operation for the skill's intended purpose of verifying TypeScript types within a project environment.
[DATA_EXPOSURE] (SAFE): The skill reads source code files and type definitions to identify errors and context. There is no evidence of attempts to access sensitive system files (e.g., credentials or configuration files) or exfiltrate data to external domains.
[INDIRECT_PROMPT_INJECTION] (SAFE): The skill processes external inputs such as compiler output and source code. While it does not define explicit boundary markers for these inputs, the risk is minimal given the specialized context of code repair. \n
Ingestion points: npm run typecheck stdout and project files read via Read and Grep. \n
Boundary markers: Absent. \n
Capability inventory: Bash (command execution), Edit (file modification), Read, Grep. \n
Sanitization: None.

type-checker