The Agent Skills Directory

[PROMPT_INJECTION]: The skill instructions and documentation focus exclusively on API design principles. There are no attempts to override agent behavior, bypass safety filters, or extract system prompts.
[COMMAND_EXECUTION]: The skill includes a Python script located at scripts/api_validator.py. Analysis of the source code confirms it is a static analysis tool that uses regex and JSON parsing to check local files for API design patterns. It does not use subprocess, os.system, or any other functions capable of executing arbitrary commands.
[DATA_EXFILTRATION]: No network operations or data transmission patterns were detected. The skill does not access sensitive system files (e.g., SSH keys, credentials) and operates entirely on local project files in a read-only manner.
[EXTERNAL_DOWNLOADS]: The skill is self-contained and does not reference any external scripts, binaries, or package managers (npm, pip) for remote downloads.
[REMOTE_CODE_EXECUTION]: The skill does not contain logic for fetching and executing remote code, nor does it use dynamic execution functions like eval() or exec() on untrusted input.

api-patterns